© 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. 15-LLAMASCOPE-RES-131K
    11. 87556
    Prev
    Next
    INDEX
    Explanations

    verbs and terms related to optimization and status improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    StringEncoding
    -0.07
    ÙĬات
    -0.07
    odb
    -0.07
    RowCount
    -0.07
    merican
    -0.07
    ób
    -0.07
    obo
    -0.07
    ODB
    -0.07
    enders
    -0.07
    ODO
    -0.07
    POSITIVE LOGITS
    ãĥ¼ãĥ«
    0.07
     Nuevo
    0.05
    dddd
    0.05
    _marshall
    0.05
    igan
    0.05
    ableObject
    0.05
    zew
    0.05
    kich
    0.05
    /report
    0.05
    dar
    0.05
    Activations Density 0.039%

    No Known Activations