© 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. 74792
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and questioning

    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
    apur
    -0.07
    Ñģем
    -0.07
    deen
    -0.07
    ValuePair
    -0.07
    ÐĴÑĸд
    -0.06
    .HTML
    -0.06
    ाश
    -0.06
    _FW
    -0.06
    asher
    -0.06
    yen
    -0.06
    POSITIVE LOGITS
     correct
    0.15
     wrong
    0.13
     incorrect
    0.13
     Correct
    0.13
    Correct
    0.12
     correctness
    0.12
    correct
    0.12
     Wrong
    0.11
     proven
    0.11
     WRONG
    0.11
    Activations Density 0.069%

    No Known Activations