© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2774
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries that begin with "what" or "how."

    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
    ton
    -0.08
    åļ
    -0.08
    /XML
    -0.08
    TON
    -0.07
    ulk
    -0.07
    ARGIN
    -0.07
    439
    -0.07
    çļ
    -0.07
    ovich
    -0.07
     itself
    -0.07
    POSITIVE LOGITS
     odds
    0.08
    erre
    0.07
     chances
    0.07
     other
    0.07
     major
    0.07
     options
    0.07
     Odds
    0.07
     expectations
    0.06
     key
    0.06
     sources
    0.06
    Activations Density 0.008%

    No Known Activations