© 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. 129129
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or lack of understanding

    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
    alo
    -0.08
    äs
    -0.07
    ioni
    -0.07
    ily
    -0.07
     Cumhur
    -0.07
    indr
    -0.06
    oons
    -0.06
    ali
    -0.06
    utow
    -0.06
    shaw
    -0.06
    POSITIVE LOGITS
     anymore
    0.08
     whether
    0.07
    abic
    0.07
     nor
    0.07
     Bair
    0.07
     how
    0.07
     Prism
    0.07
     exactly
    0.06
     ever
    0.06
    whether
    0.06
    Activations Density 0.019%

    No Known Activations