© 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. 40378
    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
    importe
    -0.07
    елÑĸ
    -0.07
    abis
    -0.07
    iland
    -0.07
    bellion
    -0.07
     treff
    -0.06
    abbr
    -0.06
    edenÃŃ
    -0.06
    iswa
    -0.06
     universe
    -0.06
    POSITIVE LOGITS
    445
    0.06
    627
    0.06
    eson
    0.06
    -inline
    0.06
    Ă
    0.06
     leader
    0.06
    충
    0.06
     åį
    0.06
     lots
    0.05
     Marathon
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.