© 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. 108267
    Prev
    Next
    INDEX
    Explanations

    strong character-driven narratives in films

    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
    azon
    -0.07
    VOKE
    -0.06
    ased
    -0.06
    zew
    -0.06
     Mighty
    -0.06
    èŃľ
    -0.06
    foon
    -0.06
    indre
    -0.05
    ursal
    -0.05
    csr
    -0.05
    POSITIVE LOGITS
    δά
    0.08
     mrt
    0.08
     performances
    0.07
    夫
    0.07
    ddf
    0.07
    è
    0.07
    ecast
    0.07
    yal
    0.07
    æģ¯
    0.07
    hra
    0.07
    Activations Density 0.021%

    No Known Activations