© 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. 58844
    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
    ibaba
    -0.07
    ixe
    -0.07
    éĸ
    -0.07
    лиÑĪ
    -0.06
     epile
    -0.06
    opp
    -0.06
    един
    -0.06
    adena
    -0.06
    rese
    -0.06
    ugins
    -0.06
    POSITIVE LOGITS
    conda
    0.07
    ches
    0.07
     lots
    0.06
     Merkez
    0.06
     Hogwarts
    0.06
     çĨ
    0.06
     DataRow
    0.06
     arte
    0.06
    hum
    0.06
    çIJ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.