© 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. 60314
    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
     omas
    -0.07
    leftright
    -0.07
    lernen
    -0.07
    .pan
    -0.07
    æİĽ
    -0.07
    argin
    -0.07
    lero
    -0.07
    æŀļ
    -0.07
    olu
    -0.07
    ÃŁe
    -0.07
    POSITIVE LOGITS
    USA
    0.07
     stif
    0.06
    936
    0.06
     Others
    0.06
    reesome
    0.06
    others
    0.06
     attrib
    0.06
     others
    0.06
    Others
    0.06
    _EV
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.