© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3567
    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
    .pointer
    -0.07
    ãģ¨ãģĨ
    -0.07
    enga
    -0.07
    èĴ
    -0.07
    ennen
    -0.07
    ugu
    -0.07
    .getSelection
    -0.07
     èĴ
    -0.07
    Steam
    -0.07
    اÙĦÙĩ
    -0.07
    POSITIVE LOGITS
    736
    0.08
    Muon
    0.07
    Qu
    0.06
    gi
    0.06
     hoc
    0.06
    vester
    0.06
    ras
    0.06
    rans
    0.06
     fellows
    0.06
     Petit
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.