© 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. 62010
    Prev
    Next
    INDEX
    Explanations

    mentions of the YAML configuration language and its associated file 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
    SES
    -0.06
    eless
    -0.06
     Shel
    -0.06
    ing
    -0.06
    ãģįãģŁ
    -0.06
     Fernando
    -0.06
    anded
    -0.06
     bread
    -0.06
    e
    -0.05
     Stad
    -0.05
    POSITIVE LOGITS
    .ov
    0.08
    yntax
    0.08
    .twig
    0.08
    rror
    0.08
    cid
    0.08
    iores
    0.08
    reste
    0.07
    _AST
    0.07
    -tm
    0.07
    ovo
    0.07
    Activations Density 0.002%

    No Known Activations