© 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. 58748
    Prev
    Next
    INDEX
    Explanations

    programming structures and data types

    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
    @a
    -0.07
    ests
    -0.07
    olders
    -0.06
    edenÃŃ
    -0.06
    ë³´ì¦Ŀê¸Ī
    -0.06
    ıa
    -0.06
     bele
    -0.06
    sj
    -0.06
    entials
    -0.06
     __("
    -0.06
    POSITIVE LOGITS
    .TryParse
    0.07
     NumberOf
    0.07
     numberOf
    0.07
    ahlen
    0.07
    ocker
    0.07
    gee
    0.06
    embros
    0.06
     numOf
    0.06
    aghetti
    0.06
    uropean
    0.06
    Activations Density 0.154%

    No Known Activations