© 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. 38461
    Prev
    Next
    INDEX
    Explanations

    criminal charges

    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
     abuses
    -0.12
     Parcel
    -0.10
    inka
    -0.10
     wrongdoing
    -0.10
     subpoena
    -0.10
    asaki
    -0.10
     taxing
    -0.10
    avers
    -0.09
    é¸
    -0.09
    Prostit
    -0.09
    POSITIVE LOGITS
     charge
    0.18
     charges
    0.16
     penalties
    0.16
     stiff
    0.15
     colony
    0.15
     à¤¸à¤ľ
    0.14
     conviction
    0.13
    charge
    0.13
    罪
    0.13
     punished
    0.13
    Activations Density 0.077%

    No Known Activations