© 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. 57047
    Prev
    Next
    INDEX
    Explanations

    instructions and actions related to posting comments or messages

    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
    -generator
    -0.07
    ç½
    -0.07
    oeff
    -0.06
    uropean
    -0.06
    æ´
    -0.06
    ipe
    -0.06
    trys
    -0.06
    antor
    -0.06
    woff
    -0.06
    ÏĦÏģα
    -0.06
    POSITIVE LOGITS
     comment
    0.10
    comment
    0.07
    _comment
    0.07
    Comment
    0.07
     Comment
    0.07
     comments
    0.07
     commentaire
    0.07
    ocker
    0.06
    orias
    0.06
    .comment
    0.06
    Activations Density 0.007%

    No Known Activations