© 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. 5965
    Prev
    Next
    INDEX
    Explanations

    phrases indicating decision-making processes and uncertainty

    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
    cre
    -0.07
    I
    -0.06
    WH
    -0.06
    elters
    -0.06
    au
    -0.06
    loven
    -0.05
    S
    -0.05
     itself
    -0.05
     WH
    -0.05
    lm
    -0.05
    POSITIVE LOGITS
     how
    0.20
     whether
    0.16
    how
    0.14
     what
    0.14
     cómo
    0.13
     ìĸ´ëĸ»ê²Į
    0.12
     why
    0.12
    å¦Ĥä½ķ
    0.12
    whether
    0.12
     Whether
    0.11
    Activations Density 0.047%

    No Known Activations