© 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. 60849
    Prev
    Next
    INDEX
    Explanations

    code attributes and identifiers related to HTML elements

    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
    ÑĽ
    -0.07
    .rt
    -0.07
     फर
    -0.07
    .ribbon
    -0.07
    ιά
    -0.06
    sert
    -0.06
     sert
    -0.06
     Ñģлиз
    -0.06
    OLLOW
    -0.06
    Ñĵ
    -0.06
    POSITIVE LOGITS
    REA
    0.07
    itsu
    0.06
    orz
    0.06
    chia
    0.06
    inka
    0.06
    pyx
    0.06
     Strauss
    0.06
    ($(".
    0.06
    DTD
    0.06
     Karl
    0.06
    Activations Density 0.001%

    No Known Activations