© 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. 11802
    Prev
    Next
    INDEX
    Explanations

    sustainable future and better place

    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
     astr
    -0.10
    æĺŃ
    -0.09
     planetary
    -0.09
     paren
    -0.09
     bam
    -0.08
    herits
    -0.08
     compromise
    -0.08
    ết
    -0.08
    .symmetric
    -0.08
    apol
    -0.08
    POSITIVE LOGITS
     habit
    0.61
     liv
    0.40
     Habit
    0.38
    hab
    0.35
     hab
    0.35
    habit
    0.33
     Hab
    0.33
     inhab
    0.30
    liv
    0.28
     hosp
    0.28
    Activations Density 0.090%

    No Known Activations