© 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. 95245
    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
    anzi
    -0.07
    vie
    -0.07
    ĥ½
    -0.06
    ìm
    -0.06
    ÄĽn
    -0.06
    ench
    -0.06
    ücken
    -0.06
    î
    -0.06
    orton
    -0.06
    sey
    -0.06
    POSITIVE LOGITS
     Finnish
    0.09
    är
    0.08
     Helsinki
    0.07
     personel
    0.07
     Finland
    0.07
    .fi
    0.07
     Rune
    0.07
     finns
    0.06
    ž
    0.06
    äh
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.