© 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. 3104
    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
    prene
    -0.07
    pta
    -0.06
    eon
    -0.05
     TimeInterval
    -0.05
    eral
    -0.05
     dung
    -0.05
    ocio
    -0.05
    eyse
    -0.05
     fac
    -0.05
    rega
    -0.05
    POSITIVE LOGITS
    AREST
    0.08
    Ñıж
    0.07
     verk
    0.07
    åĩºåĵģ
    0.07
    ãĥIJãĥ¼
    0.07
    #{@
    0.07
    retorno
    0.07
    yps
    0.07
    {}",
    0.07
    839
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.