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

    Neuronpedia

    Jacobian LensNEW
    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. 75098
    Prev
    Next
    INDEX
    Explanations

    expressions of decision-making and confidence

    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
    aji
    -0.07
    linger
    -0.07
    agner
    -0.06
    993
    -0.06
    ẫ
    -0.06
    enn
    -0.06
     STRICT
    -0.06
    wig
    -0.06
     WHATSOEVER
    -0.06
    WithURL
    -0.06
    POSITIVE LOGITS
     correct
    0.09
     correctness
    0.09
     decisions
    0.08
     OK
    0.07
     direction
    0.07
     Correct
    0.07
    correct
    0.07
     justification
    0.07
     choices
    0.07
     ok
    0.06
    Activations Density 0.036%

    No Known Activations