Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57347
    Prev
    Next
    INDEX
    Explanations

    references to websites or links

    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
    allee
    -0.07
    693
    -0.06
     kron
    -0.06
     Bulletin
    -0.06
     prescription
    -0.06
    861
    -0.06
    uese
    -0.06
    xc
    -0.06
    Closure
    -0.06
     Reflex
    -0.05
    POSITIVE LOGITS
    IGH
    0.07
    lags
    0.07
    .ALIGN
    0.06
    FIX
    0.06
    egov
    0.06
    Wunused
    0.06
    anje
    0.06
    ÑĢг
    0.06
    .Commit
    0.06
    eteria
    0.06
    Activations Density 0.000%

    No Known Activations