© 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. 72036
    Prev
    Next
    INDEX
    Explanations

    occurrences of underscores and related syntax in coding contexts

    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
    ги
    -0.07
     Lund
    -0.07
    tracked
    -0.07
    icerca
    -0.07
    enberg
    -0.07
    erne
    -0.06
    lijke
    -0.06
    CEED
    -0.06
    سÙĦ
    -0.06
    indent
    -0.06
    POSITIVE LOGITS
    burgh
    0.06
    ÅĻes
    0.06
    ienie
    0.06
    ноÑĪ
    0.05
     oasis
    0.05
    coln
    0.05
     tame
    0.05
    kap
    0.05
     Halo
    0.05
    ContentSize
    0.05
    Activations Density 0.000%

    No Known Activations