© 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. 126449
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes used 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
    ugo
    -0.07
    475
    -0.06
     Briggs
    -0.06
    BarItem
    -0.06
    lok
    -0.06
    ÑĤÑĢа
    -0.06
    lds
    -0.06
    armor
    -0.06
    folios
    -0.06
     damned
    -0.06
    POSITIVE LOGITS
    eyin
    0.08
    eyse
    0.07
    asd
    0.07
    ิà¸Ī
    0.06
    asily
    0.06
    ochen
    0.06
    ë¥
    0.06
     sails
    0.06
    icher
    0.06
    umu
    0.06
    Activations Density 0.014%

    No Known Activations