© 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. 86898
    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
     Yar
    -0.07
    aga
    -0.07
    WARE
    -0.07
     Hanson
    -0.06
    (skip
    -0.06
    antry
    -0.06
    este
    -0.06
    _UNUSED
    -0.06
    é¹
    -0.06
    VICE
    -0.05
    POSITIVE LOGITS
    ../../../
    0.09
    orer
    0.07
     èį
    0.07
    ivec
    0.07
    acic
    0.07
    ÏİÏĤ
    0.07
    roller
    0.07
    kowski
    0.06
    zew
    0.06
    ussy
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.