© 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. 230
    Prev
    Next
    INDEX
    Explanations

    delaying treatment or after release

    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
     accum
    -0.10
     incarcer
    -0.09
     incorpor
    -0.09
     interrog
    -0.09
     affair
    -0.09
    715
    -0.09
    itional
    -0.09
     miser
    -0.09
     ÑģмеÑĢ
    -0.08
    缼
    -0.08
    POSITIVE LOGITS
     entry
    0.15
     manufacture
    0.12
     publication
    0.12
     delivery
    0.11
     closure
    0.11
     orgasm
    0.11
     collapse
    0.10
     licens
    0.10
     review
    0.10
    alysis
    0.10
    Activations Density 0.140%

    No Known Activations