© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107219
    Prev
    Next
    INDEX
    Explanations

    references to data or number sequences related to health metrics and studies

    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
    cab
    -0.07
     olab
    -0.07
    ãģĨãĤĵ
    -0.07
    lendir
    -0.07
    гл
    -0.07
    /gui
    -0.07
    .mdl
    -0.07
     vidé
    -0.07
    ÑĢол
    -0.07
    umbn
    -0.07
    POSITIVE LOGITS
    outer
    0.06
    rix
    0.06
     egret
    0.05
    Ñĩини
    0.05
    ÏĦή
    0.05
    iston
    0.05
    yw
    0.05
    ativa
    0.05
    .Context
    0.05
     transient
    0.05
    Activations Density 0.011%

    No Known Activations