© 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. 121082
    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
    inis
    -0.08
    ylon
    -0.08
    ãĥ»ãĥ»ãĥ»↵↵
    -0.08
    quires
    -0.07
    .proto
    -0.07
     Hath
    -0.07
    juan
    -0.07
    ervers
    -0.07
    coe
    -0.07
    ayet
    -0.07
    POSITIVE LOGITS
     fucking
    0.06
     Brock
    0.06
     zá
    0.06
    Âĩ
    0.06
     maybe
    0.06
     Vad
    0.05
     like
    0.05
    ypsy
    0.05
     yes
    0.05
    aram
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.