© 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. 78222
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically commas and quotation marks

    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
    .getInteger
    -0.07
    abel
    -0.07
    OptionsMenu
    -0.06
     pÅĻitom
    -0.06
    é¡į
    -0.06
    isser
    -0.06
    ÑģÑĮ
    -0.06
    steder
    -0.06
     meisten
    -0.06
    .setParent
    -0.06
    POSITIVE LOGITS
    ing
    0.08
    Åij
    0.07
    ingt
    0.07
    ÂĿ
    0.07
    nbsp
    0.07
    ijo
    0.06
    avic
    0.06
    IELDS
    0.06
    pearance
    0.06
    ota
    0.06
    Activations Density 0.078%

    No Known Activations