© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56273
    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
     Daly
    -0.06
    aterno
    -0.06
     Sun
    -0.06
    783
    -0.06
    erea
    -0.06
     Gui
    -0.06
     Remix
    -0.06
    veal
    -0.06
    yny
    -0.05
    tero
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.08
    _literals
    0.08
    ÐľÐŀ
    0.07
    RIX
    0.07
    orelease
    0.07
    izzer
    0.07
    .www
    0.07
    .Author
    0.07
    ife
    0.06
     Äijá»Ŀi
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.