© 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. 14819
    Prev
    Next
    INDEX
    Explanations

    pointers to online services for booking and purchasing tickets

    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
    OMIC
    -0.06
    #endregion
    -0.06
     Levin
    -0.06
    å«Į
    -0.06
    poses
    -0.06
    antine
    -0.06
    ruh
    -0.06
    ίγ
    -0.06
    .react
    -0.06
     ins
    -0.06
    POSITIVE LOGITS
    asco
    0.07
    zman
    0.06
    ofilm
    0.06
    resher
    0.06
    atur
    0.06
    uper
    0.06
    /off
    0.06
     Mang
    0.06
    (AdapterView
    0.06
    .annotate
    0.06
    Activations Density 0.009%

    No Known Activations