Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96178
    Prev
    Next
    INDEX
    Explanations

    elements related to form handling in web development

    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
    ç¬
    -0.07
    erot
    -0.07
    jang
    -0.07
    cratch
    -0.07
    ayscale
    -0.07
    otton
    -0.07
    argout
    -0.07
    ÙĪØ²
    -0.06
    asco
    -0.06
    clerosis
    -0.06
    POSITIVE LOGITS
    odo
    0.06
    _MACRO
    0.06
    uru
    0.06
    ูà¹Ī
    0.06
    #
    0.06
     laut
    0.06
     Adolf
    0.06
    Patterns
    0.06
    ensburg
    0.06
     patterns
    0.06
    Activations Density 0.004%

    No Known Activations