© 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. 4880
    Prev
    Next
    INDEX
    Explanations

    references to names, lists, or databases in the context of participation or membership

    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
    weet
    -0.07
    PO
    -0.07
    ÄįÃŃ
    -0.07
    954
    -0.06
    empo
    -0.06
     Spike
    -0.06
    LOC
    -0.06
    éļ
    -0.06
    .ml
    -0.06
    theses
    -0.06
    POSITIVE LOGITS
     database
    0.07
     roster
    0.07
    ÏĦÏī
    0.07
     ë°°
    0.07
     Database
    0.06
    омеÑĤ
    0.06
    arent
    0.06
     rolls
    0.06
     Pearce
    0.06
    ROUP
    0.06
    Activations Density 0.007%

    No Known Activations