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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118741
    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
    é§
    -0.07
    aign
    -0.06
    á»ĭnh
    -0.06
     Woj
    -0.06
     fucked
    -0.06
    hpp
    -0.06
    lech
    -0.06
     Quote
    -0.05
     falling
    -0.05
    御
    -0.05
    POSITIVE LOGITS
    zell
    0.07
    SION
    0.07
    plies
    0.07
    izer
    0.06
    kol
    0.06
     ngang
    0.06
    minate
    0.06
    venta
    0.06
    bron
    0.06
    ìķĪ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.