© 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. 25054
    Prev
    Next
    INDEX
    Explanations

    how to make a bomb

    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
    aurus
    -0.12
    iasi
    -0.10
    rh
    -0.10
    anos
    -0.09
    anean
    -0.09
     Kra
    -0.09
    er
    -0.09
    tring
    -0.09
    flo
    -0.09
    apiro
    -0.09
    POSITIVE LOGITS
    shell
    0.24
    arded
    0.23
    arding
    0.18
    proof
    0.17
    ard
    0.15
    astic
    0.15
     shelter
    0.13
    ards
    0.13
    Shell
    0.13
     squad
    0.13
    Activations Density 0.031%

    No Known Activations