© 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. 124633
    Prev
    Next
    INDEX
    Explanations

    references to genetic relationships and historical influences on domestic species

    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
    zik
    -0.08
    à¥Īद
    -0.08
    addock
    -0.07
     ç±
    -0.07
    rud
    -0.07
    qus
    -0.07
    chet
    -0.07
    ãĥ³ãĥĩ
    -0.07
     ÙħÙĨزÙĦ
    -0.07
    regunta
    -0.07
    POSITIVE LOGITS
     mixing
    0.08
     Mixing
    0.07
    dana
    0.06
    .mix
    0.06
     during
    0.06
     migrations
    0.06
     forced
    0.06
     kel
    0.06
     exchange
    0.06
     forc
    0.06
    Activations Density 0.015%

    No Known Activations