© 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. 84614
    Prev
    Next
    INDEX
    Explanations

    references to specific details or qualifications in a discussion

    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
     meiden
    -0.08
     derivation
    -0.07
    eyim
    -0.06
    idel
    -0.06
    αÏģά
    -0.06
    enco
    -0.06
    viar
    -0.06
    (dl
    -0.06
     âŀ
    -0.06
    олÑĮ
    -0.06
    POSITIVE LOGITS
     converse
    0.07
    ĵåIJį
    0.06
    ÃŃrk
    0.06
     appearances
    0.06
    irie
    0.06
    VERSE
    0.06
    ifice
    0.06
    apan
    0.06
     reverse
    0.06
    panion
    0.06
    Activations Density 0.094%

    No Known Activations