© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57121
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    onga
    -0.09
    unas
    -0.06
     lately
    -0.06
    &s
    -0.06
    930
    -0.06
    qui
    -0.06
    573
    -0.06
    zan
    -0.05
    392
    -0.05
    azor
    -0.05
    POSITIVE LOGITS
    bette
    0.08
    icana
    0.08
    swick
    0.07
    .Abstractions
    0.07
    uppy
    0.07
    wyn
    0.07
    isté
    0.07
    μιÏĥ
    0.06
    ieux
    0.06
    heim
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.