© 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. 129137
    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
    warts
    -0.07
    onde
    -0.07
    ramids
    -0.07
    ific
    -0.07
    apolis
    -0.06
     airports
    -0.06
     ä¹
    -0.06
     аÑĥд
    -0.06
    hta
    -0.06
    ะ
    -0.06
    POSITIVE LOGITS
     chip
    0.06
     Faul
    0.06
    ORN
    0.06
    oron
    0.06
    rix
    0.06
    aland
    0.06
    aber
    0.06
    redd
    0.06
    egral
    0.06
    akra
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.