© 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. 18061
    Prev
    Next
    INDEX
    Explanations

    terms related to harm and harmful effects

    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
    gether
    -0.08
    itis
    -0.07
    ader
    -0.07
    æ¡£
    -0.07
    ADER
    -0.07
    haul
    -0.07
    .Bunifu
    -0.07
    ural
    -0.07
    naire
    -0.06
    iro
    -0.06
    POSITIVE LOGITS
    fully
    0.11
    lessly
    0.09
    aceutical
    0.08
    sworth
    0.08
    ful
    0.07
    ERSHEY
    0.07
    spot
    0.07
    FUL
    0.07
    mmm
    0.07
    |h
    0.07
    Activations Density 0.006%

    No Known Activations