© 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. 86679
    Prev
    Next
    INDEX
    Explanations

    structured programming concepts and constructs

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

    Whitespace characters, method prefixes, and syntax elements in programming code blocks, typically appearing at line beginnings or in method definitions.

    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
    ahoma
    -0.07
    itters
    -0.06
    utherland
    -0.06
    throw
    -0.06
    ecs
    -0.06
    anela
    -0.06
    impl
    -0.06
    rama
    -0.06
     dart
    -0.06
     Dot
    -0.06
    POSITIVE LOGITS
    vÃŃc
    0.08
     èIJ
    0.06
    ữ
    0.06
    adesh
    0.06
    obl
    0.06
     замов
    0.06
    _ASSUME
    0.06
     çĽ
    0.06
    apor
    0.06
    iamond
    0.06
    Activations Density 0.021%

    No Known Activations