© 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. 129456
    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
    اÙĪت
    -0.06
    ddy
    -0.06
    arta
    -0.06
    Extern
    -0.06
    onga
    -0.06
    bee
    -0.06
    obl
    -0.06
    comb
    -0.06
    ;element
    -0.06
     идеÑĤ
    -0.06
    POSITIVE LOGITS
     lawy
    0.08
    unset
    0.08
    992
    0.07
    spaces
    0.07
    abilities
    0.07
     encounter
    0.07
     spaces
    0.07
     networks
    0.07
    ftar
    0.07
     labour
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.