© 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. 52380
    Prev
    Next
    INDEX
    Explanations

    conflict, attack, fight

    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
    esto
    -0.10
     tro
    -0.10
     pl
    -0.10
     Bomb
    -0.10
     invading
    -0.09
    asto
    -0.09
    Bomb
    -0.09
     misuse
    -0.08
     Tro
    -0.08
     vague
    -0.08
    POSITIVE LOGITS
     fight
    0.16
     attack
    0.15
     attacked
    0.13
     firefight
    0.13
     Fight
    0.12
    fight
    0.12
    æĪĺæĸĹ
    0.12
     engagement
    0.12
     outnumber
    0.11
     backup
    0.11
    Activations Density 0.037%

    No Known Activations