© 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. 87707
    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
    ŀæĢ§
    -0.07
     discrete
    -0.06
     Îī
    -0.06
     chu
    -0.06
    ãĥ¼ãĥł
    -0.06
    loquent
    -0.06
     breakout
    -0.05
    erty
    -0.05
     Detail
    -0.05
    ategy
    -0.05
    POSITIVE LOGITS
    unsch
    0.07
     ydk
    0.07
    myp
    0.07
    ิà¸ķร
    0.07
    ôi
    0.07
     tôi
    0.07
    CharArray
    0.07
     my
    0.07
    ãĤ´ãĥª
    0.06
    ancellationToken
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.