© 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 EvalsExportsAPI 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. 85317
    Prev
    Next
    INDEX
    Explanations

    references to file sizes and document specifications

    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
    et
    -0.06
    inch
    -0.06
    ait
    -0.06
     contact
    -0.06
    acock
    -0.06
     Hundred
    -0.06
    iral
    -0.05
    ition
    -0.05
     type
    -0.05
    yer
    -0.05
    POSITIVE LOGITS
    chwitz
    0.08
    hev
    0.08
    ipi
    0.07
    krom
    0.07
    rench
    0.07
     عÙĤد
    0.07
    /frame
    0.07
     ç¢
    0.07
    PLE
    0.07
    agit
    0.07
    Activations Density 0.002%

    No Known Activations