© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75274
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters within text

    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
    \brief
    -0.09
     ÐłÐµ
    -0.08
    ÙĬØ©
    -0.07
    [`
    -0.07
    elves
    -0.07
    HandlerContext
    -0.07
     Slut
    -0.06
    ibName
    -0.06
    Ñħов
    -0.06
    iasm
    -0.06
    POSITIVE LOGITS
    iselect
    0.06
     titled
    0.06
    Âłmi
    0.06
     exped
    0.06
    jid
    0.05
     Kaf
    0.05
    íıŃ
    0.05
     anticipate
    0.05
    /Foundation
    0.05
     mi
    0.05
    Activations Density 0.013%

    No Known Activations