© 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. 76238
    Prev
    Next
    INDEX
    Explanations

    HTML code related to navigation menus in web documents

    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
    orne
    -0.07
    ynes
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
    whereIn
    -0.07
    lect
    -0.07
    vÃŃ
    -0.06
    ãĥ©ãĥĥãĤ¯
    -0.06
    ombre
    -0.06
    itionally
    -0.06
     ÙĨÙĪÙĬس
    -0.06
    POSITIVE LOGITS
    ÑģÑĤе
    0.06
    assa
    0.06
    unes
    0.06
    ChangedEventArgs
    0.06
    代
    0.06
    967
    0.06
     êµ
    0.06
     Simpl
    0.05
     easiest
    0.05
     Dalton
    0.05
    Activations Density 0.003%

    No Known Activations