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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5601
    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
    ANGER
    -0.06
    kili
    -0.06
     contrast
    -0.06
    ARS
    -0.06
    ire
    -0.06
    iec
    -0.06
    oj
    -0.06
    bellion
    -0.05
     firing
    -0.05
    ANTE
    -0.05
    POSITIVE LOGITS
    usto
    0.07
    .ribbon
    0.07
     Poh
    0.06
    494
    0.06
    igrams
    0.06
    ittest
    0.06
     Scalars
    0.06
    esz
    0.06
    omanip
    0.06
    ought
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.