© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 62843
    Prev
    Next
    INDEX
    Explanations

    harmful acts violence suicide aggression

    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
    ADDE
    -0.10
     èĬ
    -0.09
     Gust
    -0.09
    afi
    -0.09
    349
    -0.09
    azz
    -0.09
     temper
    -0.09
     Mixed
    -0.09
    avan
    -0.09
    ฤ
    -0.08
    POSITIVE LOGITS
     problem
    0.12
     happens
    0.12
     prevention
    0.11
     exact
    0.11
     rates
    0.10
     statistics
    0.10
     touches
    0.10
    mars
    0.10
     seriousness
    0.10
     devast
    0.10
    Activations Density 0.144%

    No Known Activations