© 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. 106577
    Prev
    Next
    INDEX
    Explanations

    object references and data structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Special characters or tokens that serve as delimiters, file extensions, or syntax elements in programming code and structured data formats.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    zee
    -0.07
    avad
    -0.07
    ector
    -0.06
     Schiff
    -0.06
    UnitOfWork
    -0.06
    imple
    -0.06
     Fog
    -0.06
    LIK
    -0.06
    ither
    -0.06
    ListOf
    -0.06
    POSITIVE LOGITS
     ::=
    0.08
     seins
    0.07
    ảo
    0.07
    0.07
    ùy
    0.07
    adesh
    0.06
    &apos
    0.06
    tainment
    0.06
    ::~
    0.06
     =================================================================================
    0.06
    Activations Density 0.366%

    No Known Activations