© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 85891
    Prev
    Next
    INDEX
    Explanations

    topics related to societal issues and challenges

    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
    pson
    -0.07
    aniem
    -0.07
    anel
    -0.07
    -badge
    -0.07
    ymes
    -0.07
    amoto
    -0.07
    abei
    -0.06
    ielding
    -0.06
    ehr
    -0.06
    iego
    -0.06
    POSITIVE LOGITS
     shouldn
    0.07
     odds
    0.07
     chances
    0.07
    cannot
    0.06
     unlikely
    0.06
     it
    0.06
    $$$$
    0.06
     cannot
    0.06
     wouldn
    0.06
     merg
    0.06
    Activations Density 0.075%

    No Known Activations