© 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. 104256
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names, particularly those related to individuals and geographical locations

    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
    ãģĿãģĹãģ¦
    -0.09
    eger
    -0.07
    ладÑĥ
    -0.07
    /cop
    -0.07
    ceb
    -0.07
    ãĤĵãģ¨
    -0.07
    niž
    -0.07
    ãĤ¹ãĤ¿ãĥ¼
    -0.07
    lenir
    -0.07
    ä¿
    -0.07
    POSITIVE LOGITS
     See
    0.07
    See
    0.07
     ?,
    0.07
    âĢħ
    0.07
    uentes
    0.07
    ':
    0.06
     –
    0.06
    ↵↵
    0.06
    ":
    0.06
     â
    0.06
    Activations Density 0.011%

    No Known Activations