© 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. 17275
    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
    ди
    -0.06
    eri
    -0.06
    cher
    -0.06
    nown
    -0.06
     chiefly
    -0.06
    izza
    -0.05
    exion
    -0.05
    its
    -0.05
    mask
    -0.05
    -esque
    -0.05
    POSITIVE LOGITS
    /Branch
    0.08
    ideographic
    0.07
    üz
    0.07
    bsub
    0.07
    latlong
    0.07
     ê´
    0.07
    ipsis
    0.07
    ControlEvents
    0.07
    ôi
    0.07
    ');?>"
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.