© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13617
    Prev
    Next
    INDEX
    Explanations

    violent attack

    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
    hek
    -0.10
    era
    -0.09
    aven
    -0.09
    stp
    -0.09
    765
    -0.08
    ignon
    -0.08
     Kardashian
    -0.08
    onom
    -0.08
     Tk
    -0.08
    652
    -0.08
    POSITIVE LOGITS
     titular
    0.15
    olik
    0.10
    Â
    0.10
    ÂĢÂĢ
    0.09
    opleft
    0.09
    ¦æĥħ
    0.09
    \xe
    0.08
     CascadeType
    0.08
    ¶Į
    0.08
    ãģĹãĤĥ
    0.08
    Activations Density 0.085%

    No Known Activations