© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88146
    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
    enh
    -0.06
    pl
    -0.06
     bleeding
    -0.06
    "\↵
    -0.06
    HRESULT
    -0.06
    china
    -0.06
     Weaver
    -0.06
     Ashley
    -0.06
    оба
    -0.06
    bour
    -0.06
    POSITIVE LOGITS
    itler
    0.07
    åĵ¡
    0.07
    ÙĤÙĩ
    0.07
    _reserved
    0.06
    Winvalid
    0.06
    EIF
    0.06
    åı¸
    0.06
    ERICA
    0.06
     +:+
    0.06
     clen
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.