© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96629
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns and notable terms related to governance and societal issues

    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
    osten
    -0.07
    ordion
    -0.07
    okes
    -0.07
    ardon
    -0.07
    osto
    -0.07
    avigation
    -0.07
    nier
    -0.06
    ords
    -0.06
    icher
    -0.06
    dealloc
    -0.06
    POSITIVE LOGITS
     courtesy
    0.06
    URA
    0.06
    239
    0.05
    {:
    0.05
     proh
    0.05
    ëıħ
    0.05
     cá»ij
    0.05
     originals
    0.05
     colabor
    0.05
    _CONN
    0.05
    Activations Density 0.000%

    No Known Activations