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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127095
    Prev
    Next
    INDEX
    Explanations

    phrases related to custom products and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Shares
    -0.06
    olan
    -0.06
     equilibrium
    -0.06
    .scalablytyped
    -0.06
    umo
    -0.06
    UPDATED
    -0.06
    .Parser
    -0.06
     Manuals
    -0.06
     UPDATED
    -0.05
    aises
    -0.05
    POSITIVE LOGITS
     Custom
    0.11
     custom
    0.10
    custom
    0.10
     customization
    0.09
    Custom
    0.09
     Customize
    0.09
     bespoke
    0.09
    /custom
    0.09
    (custom
    0.08
    ãĥ³ãĤ¸
    0.08
    Activations Density 0.016%

    No Known Activations