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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5341
    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
    roids
    -0.07
    orphic
    -0.07
    mey
    -0.07
    ãĥ
    -0.06
    azzo
    -0.06
    dbh
    -0.06
    åĬŁ
    -0.06
     Spam
    -0.06
    raya
    -0.06
    olian
    -0.06
    POSITIVE LOGITS
    fu
    0.07
    g
    0.06
    ag
    0.06
     McCart
    0.06
     Willis
    0.06
     Coff
    0.06
    fy
    0.06
     Circ
    0.06
     nap
    0.06
     Fu
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.