© 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. 78490
    Prev
    Next
    INDEX
    Explanations

    references to groups and categories

    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
     )↵↵↵↵↵↵↵↵
    -0.08
     sobÄĽ
    -0.07
    erif
    -0.07
    uating
    -0.07
    มà¸Ń
    -0.07
     addCriterion
    -0.07
    ĥn
    -0.07
    REA
    -0.07
    ñana
    -0.07
    yum
    -0.07
    POSITIVE LOGITS
    apiro
    0.06
    stral
    0.06
    000
    0.06
    redo
    0.06
     of
    0.06
    olean
    0.06
    .parsers
    0.05
     cookies
    0.05
    aliz
    0.05
     Bond
    0.05
    Activations Density 0.022%

    No Known Activations