© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94183
    Prev
    Next
    INDEX
    Explanations

    code elements and their functions within a programming context

    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
    ewise
    -0.07
    wner
    -0.07
    VC
    -0.06
    áÄį
    -0.06
    ects
    -0.06
    weather
    -0.06
    esson
    -0.06
    iddle
    -0.06
    hee
    -0.06
    plib
    -0.06
    POSITIVE LOGITS
    MBProgressHUD
    0.07
     Wilkinson
    0.06
    804
    0.06
    defgroup
    0.06
    vrier
    0.06
    hardt
    0.06
    odore
    0.06
    ży
    0.06
    iswa
    0.06
    gam
    0.06
    Activations Density 0.011%

    No Known Activations