© 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. 38631
    Prev
    Next
    INDEX
    Explanations

    syntax and structure relevant to programming and code documentation

    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
    atorium
    -0.07
    ollen
    -0.07
    å¤
    -0.07
    iropr
    -0.07
    ementia
    -0.06
    lush
    -0.06
    orks
    -0.06
    eldon
    -0.06
    ļ
    -0.06
    RLF
    -0.06
    POSITIVE LOGITS
    root
    0.06
     cones
    0.06
    zdy
    0.06
     Bench
    0.06
    tg
    0.06
    rine
    0.06
    avigate
    0.06
    éĿ
    0.06
     taper
    0.06
    esine
    0.06
    Activations Density 0.002%

    No Known Activations