© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 87416
    Prev
    Next
    INDEX
    Explanations

    financial implications and support details related to software products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Specific words or phrases that signal transitions or connections in technical or business content, particularly around product lifecycles, updates, and service changes. Words like "is", "will be", "continue to", "when the", "decide to remove", "for", "since there", "being", "by", "out", "parts for", "if", "maintain", "then" frequently appear in contexts describing product status changes, discontinuations, deprecations, or technical dependencies.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ozor
    -0.08
    .onError
    -0.08
    ãĥ¬ãĥĵ
    -0.07
     Ñģид
    -0.07
    ãĥ«ãĤ¯
    -0.07
    escaping
    -0.07
    .retry
    -0.07
    ONO
    -0.07
    æı®
    -0.07
    Credentials
    -0.07
    POSITIVE LOGITS
     support
    0.07
     discontinued
    0.07
     legacy
    0.07
     discontin
    0.07
     relic
    0.06
     maintenance
    0.06
    ianne
    0.06
    Deprecated
    0.06
     indef
    0.06
     
    0.06
    Activations Density 0.077%

    No Known Activations