© 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. 126201
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript syntax elements in a document

    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
    lah
    -0.06
    را
    -0.06
    697
    -0.06
     Thrones
    -0.06
     Weinstein
    -0.06
    æ¸Ī
    -0.06
    576
    -0.06
    97
    -0.05
     ra
    -0.05
     meteor
    -0.05
    POSITIVE LOGITS
    ÑĢаÑĤно
    0.08
    TagName
    0.08
    _TITLE
    0.08
    unta
    0.08
    -valu
    0.07
    .title
    0.07
    isoner
    0.07
    title
    0.07
    SetTitle
    0.07
    عÙĨÙĪاÙĨ
    0.07
    Activations Density 0.013%

    No Known Activations