© 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 EvalsExportsinterp-engineNEWAPI 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. 17034
    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
     lived
    -0.07
    ammer
    -0.06
    664
    -0.06
     baked
    -0.06
     incentiv
    -0.06
    )[:
    -0.05
     EAR
    -0.05
     schema
    -0.05
    857
    -0.05
     base
    -0.05
    POSITIVE LOGITS
    berman
    0.10
     sez
    0.08
    GENCY
    0.08
    geme
    0.08
     routines
    0.08
    gency
    0.08
    isle
    0.07
    routine
    0.07
    bish
    0.07
    outines
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.