© 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. 28993
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of confusion or uncertainty

    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
    ɵ
    -0.07
    omination
    -0.06
    lad
    -0.06
    aversal
    -0.06
    -addons
    -0.06
    gth
    -0.06
    SplitOptions
    -0.06
    ãĥ³ãĥĨãĤ£
    -0.06
    lsi
    -0.06
    IFn
    -0.06
    POSITIVE LOGITS
     missed
    0.09
     missing
    0.09
     am
    0.08
    miss
    0.08
    Missing
    0.08
     Am
    0.07
    missing
    0.07
     Missing
    0.07
     error
    0.07
     misses
    0.07
    Activations Density 0.008%

    No Known Activations