© 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. 86317
    Prev
    Next
    INDEX
    Explanations

    syntax elements and structure in programming code

    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
    ÙĪÛĮد
    -0.06
    ug
    -0.06
    466
    -0.06
    amac
    -0.06
    llen
    -0.06
    Ưá»
    -0.06
    isci
    -0.06
    unn
    -0.06
    cape
    -0.06
    enant
    -0.06
    POSITIVE LOGITS
    panion
    0.06
    isko
    0.06
     Phonetic
    0.06
    /store
    0.06
    getBytes
    0.06
    igli
    0.06
    iban
    0.06
    endregion
    0.06
    endas
    0.06
    £¨
    0.05
    Activations Density 0.004%

    No Known Activations