© 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. 14546
    Prev
    Next
    INDEX
    Explanations

    offensive or harmful content

    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
     oceans
    -0.15
     oils
    -0.15
     oxygen
    -0.14
    .setObjectName
    -0.14
    .opengl
    -0.13
    )object
    -0.13
     oven
    -0.12
     Osmanlı
    -0.12
     officers
    -0.12
     officer
    -0.12
    POSITIVE LOGITS
    (Op
    0.10
    OPT
    0.10
     unordered
    0.10
    (OP
    0.10
     operand
    0.10
     unofficial
    0.09
    Occ
    0.09
     Operand
    0.09
     Oper
    0.09
    operand
    0.09
    Activations Density 0.201%

    No Known Activations