© 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. 87468
    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
    pite
    -0.08
    chsel
    -0.07
    loff
    -0.07
    eel
    -0.07
    itti
    -0.06
     trotz
    -0.06
     $
    -0.06
     despite
    -0.06
     begin
    -0.06
     Jacket
    -0.06
    POSITIVE LOGITS
     Rif
    0.07
     pÅĻiÄįemž
    0.07
    .jsoup
    0.07
     Member
    0.07
     nhiá»ħm
    0.06
    provided
    0.06
    ีà¸ļ
    0.06
    polator
    0.06
    âĸłâĸł
    0.06
     Saga
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.