© 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. 17-LLAMASCOPE-RES-131K
    11. 118783
    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
     OpCode
    -0.07
    orre
    -0.07
    _tbl
    -0.07
     ----------------------------------------------------------------------------↵
    -0.07
    roti
    -0.07
     respective
    -0.07
    oldt
    -0.07
    plain
    -0.07
    (es
    -0.07
    _HINT
    -0.07
    POSITIVE LOGITS
    ait
    0.06
     ð
    0.06
     bleach
    0.06
     famously
    0.06
     Mach
    0.06
    ax
    0.06
     intervening
    0.05
    gfx
    0.05
    icks
    0.05
    arrow
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.