© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53715
    Prev
    Next
    INDEX
    Explanations

    references to probabilities and uncertainties regarding outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     phenomen
    -0.07
     gross
    -0.06
    /lists
    -0.06
    ivos
    -0.06
     physic
    -0.06
    çĮľ
    -0.06
     phen
    -0.06
    ",__
    -0.06
    _Element
    -0.06
     suspected
    -0.06
    POSITIVE LOGITS
     odds
    0.12
     chances
    0.12
     likelihood
    0.11
     Odds
    0.11
     probability
    0.11
     chance
    0.10
     probabilities
    0.10
     Chance
    0.09
    probability
    0.09
    Chance
    0.09
    Activations Density 0.009%

    No Known Activations