© 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. 15-LLAMASCOPE-RES-131K
    11. 27142
    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
    ies
    -0.06
    urn
    -0.06
    illi
    -0.06
    ht
    -0.06
    uit
    -0.05
     Alt
    -0.05
     Lies
    -0.05
    udios
    -0.05
     Chicken
    -0.05
    us
    -0.05
    POSITIVE LOGITS
    ffee
    0.09
    obao
    0.08
    GenerationStrategy
    0.08
    rawer
    0.07
    /trunk
    0.07
    ompiler
    0.07
    inality
    0.07
    ãĥ¼ãĥĸ
    0.07
    ffa
    0.07
    fen
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.