© 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. 34269
    Prev
    Next
    INDEX
    Explanations

    intentionally harmful actions

    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
    dü
    -0.09
     automatically
    -0.09
    orage
    -0.09
    awy
    -0.09
     automatic
    -0.09
    -deals
    -0.09
    coe
    -0.09
    elier
    -0.09
    뢰
    -0.08
    /new
    -0.08
    POSITIVE LOGITS
     effort
    0.12
    /un
    0.11
    inka
    0.10
    fully
    0.10
     afore
    0.10
    /man
    0.10
     seek
    0.09
     obt
    0.09
     efforts
    0.09
    /random
    0.09
    Activations Density 0.035%

    No Known Activations