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

    Neuronpedia

    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. 70750
    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
     colors
    -0.07
     flavors
    -0.07
     honors
    -0.07
     honored
    -0.07
     flavor
    -0.06
     Flavor
    -0.06
     Doctor
    -0.06
     Uncategorized
    -0.06
     armor
    -0.06
    è£ħ
    -0.06
    POSITIVE LOGITS
    usercontent
    0.08
     Parti
    0.08
    ivec
    0.08
     gazet
    0.08
     Singap
    0.07
     SGD
    0.07
    ç¬
    0.07
     Shapiro
    0.07
    оÑĢоз
    0.07
    .hr
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.