© 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. 15-LLAMASCOPE-RES-131K
    11. 86449
    Prev
    Next
    INDEX
    Explanations

    possessive nouns and pronouns associated with individuals

    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
    uien
    -0.07
     contrast
    -0.06
    iyan
    -0.06
    anch
    -0.06
    ahat
    -0.06
     sire
    -0.05
    egov
    -0.05
     contrasts
    -0.05
    vine
    -0.05
    otten
    -0.05
    POSITIVE LOGITS
    ehr
    0.07
    Ä±ÅŁÄ±k
    0.07
    ืà¹Ī
    0.07
    ãĥĥãĤ«ãĥ¼
    0.07
    ãĥ³ãĤ¸
    0.07
    conti
    0.07
     office
    0.06
    NCY
    0.06
    ramer
    0.06
     ransom
    0.06
    Activations Density 0.021%

    No Known Activations