© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38392
    Prev
    Next
    INDEX
    Explanations

    trusted entities or connections

    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
    Negative Logits
     Rosa
    -0.11
    _JS
    -0.11
    arness
    -0.10
    arching
    -0.09
     Gaw
    -0.08
     Danh
    -0.08
    393
    -0.08
    ITIES
    -0.08
    à¸ĵ
    -0.08
    avit
    -0.08
    POSITIVE LOGITS
     adults
    0.14
    /lic
    0.14
     source
    0.14
    worth
    0.13
     individuals
    0.12
     sources
    0.11
    edo
    0.11
     friend
    0.11
     adult
    0.11
    /app
    0.11
    Activations Density 0.012%

    No Known Activations