© 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. 125643
    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
    https
    -0.08
     https
    -0.06
    curity
    -0.06
     Dob
    -0.06
     stub
    -0.06
     Friedrich
    -0.05
     âĢ¯
    -0.05
     Commentary
    -0.05
     Fuller
    -0.05
    i
    -0.05
    POSITIVE LOGITS
    imu
    0.08
    toolbox
    0.07
    parator
    0.07
    ë²Ī
    0.07
    ething
    0.07
    slideDown
    0.07
     âĢª
    0.07
    .Undef
    0.07
    /xhtml
    0.07
    bulan
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.