© 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. 64922
    Prev
    Next
    INDEX
    Explanations

    mad, crazy, unhinged

    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
    Negative Logits
    å¥ĩ
    -0.10
    unset
    -0.10
    icious
    -0.09
     compromising
    -0.09
     ing
    -0.09
     conscious
    -0.09
    POCH
    -0.09
     Isa
    -0.09
     Freak
    -0.09
    iram
    -0.08
    POSITIVE LOGITS
     abandon
    0.15
     asylum
    0.14
     amounts
    0.14
     mad
    0.12
    /gen
    0.12
     wild
    0.11
    -eyed
    0.11
     antics
    0.11
    -making
    0.11
    yy
    0.11
    Activations Density 0.051%

    No Known Activations