© 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. 57984
    Prev
    Next
    INDEX
    Explanations

    the murder

    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
     Thief
    -0.13
     massac
    -0.13
     thief
    -0.12
     thieves
    -0.12
     suicidal
    -0.12
    destruct
    -0.11
    ç½ļ
    -0.10
     annihil
    -0.10
    arend
    -0.10
     Terror
    -0.10
    POSITIVE LOGITS
     murder
    0.37
     killing
    0.35
     kill
    0.28
    æĿĢ
    0.28
    殺
    0.28
    mur
    0.27
     mur
    0.24
     killed
    0.24
     kills
    0.24
    Mur
    0.23
    Activations Density 0.080%

    No Known Activations