© 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. 2286
    Prev
    Next
    INDEX
    Explanations

    toxic or poisonous

    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
     toxin
    -0.14
     toxins
    -0.11
    isode
    -0.10
    erg
    -0.10
    lyph
    -0.10
    privation
    -0.10
    reck
    -0.09
     actionTypes
    -0.09
    ustry
    -0.09
    adÃŃ
    -0.09
    POSITIVE LOGITS
    ological
    0.19
    ity
    0.19
    ities
    0.17
    ology
    0.16
    ologically
    0.16
    icity
    0.15
    ants
    0.15
    idade
    0.15
    /to
    0.14
    ant
    0.14
    Activations Density 0.020%

    No Known Activations