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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129011
    Prev
    Next
    INDEX
    Explanations

    information related to healthcare services and reference materials

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

    Text describing digital information access methods, particularly phrases about searching, looking up, or retrieving information through online tools, reference materials, or databases.

    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
    nze
    -0.07
    ikel
    -0.07
    idding
    -0.07
    ContextHolder
    -0.07
    .EventArgs
    -0.06
     Visibility
    -0.06
    #__
    -0.06
    ros
    -0.06
    รà¸ĵ
    -0.06
    éĢ
    -0.06
    POSITIVE LOGITS
     reference
    0.11
    ency
    0.10
    .reference
    0.09
    pedia
    0.08
     Reference
    0.08
    reference
    0.08
    .info
    0.08
     enc
    0.08
    æŁ¥
    0.08
    /reference
    0.08
    Activations Density 0.092%

    No Known Activations