© 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. 94889
    Prev
    Next
    INDEX
    Explanations

    references to the publication status of documents and their availability

    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
     Ramp
    -0.08
    igest
    -0.07
    ween
    -0.07
    jur
    -0.07
    ãĤĦãģĻ
    -0.07
    ieur
    -0.06
    asury
    -0.06
    ulumi
    -0.06
    161
    -0.06
    Indented
    -0.06
    POSITIVE LOGITS
    ilden
    0.08
    undles
    0.07
    sak
    0.06
     sickness
    0.06
     ëĸ¨ìĸ´
    0.06
    ema
    0.06
     Sacred
    0.06
     Sick
    0.06
     "-//
    0.06
    à¹Ħà¸Ł
    0.06
    Activations Density 0.001%

    No Known Activations