© 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. 40802
    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
    esian
    -0.06
    [
    -0.06
     NSS
    -0.06
    inois
    -0.05
     *
    -0.05
    EAR
    -0.05
    early
    -0.05
     Tay
    -0.05
    ì°©
    -0.05
    zek
    -0.05
    POSITIVE LOGITS
     Drag
    0.08
    ãĤĵãģ¨
    0.07
    Touches
    0.07
    allis
    0.07
    udent
    0.07
    #ac
    0.07
    lus
    0.07
    ëĤĺìļĶ
    0.06
    NullException
    0.06
    _EP
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.