© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 32760
    Prev
    Next
    INDEX
    Explanations

    feeling ignored or angry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disqualified
    -0.12
    aku
    -0.11
     suspended
    -0.09
     discouraged
    -0.09
     overst
    -0.09
    esc
    -0.09
    876
    -0.09
    pluck
    -0.09
     distressed
    -0.09
     traumat
    -0.09
    POSITIVE LOGITS
     treated
    0.22
     mist
    0.21
     shaft
    0.19
     victim
    0.18
     malt
    0.17
    -treated
    0.16
     slight
    0.16
    ignored
    0.16
     behand
    0.16
    reated
    0.15
    Activations Density 0.120%

    No Known Activations