© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    field, subfield, subset

    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
     benchmark
    -0.10
     Mold
    -0.09
     Bols
    -0.09
    ãĤ¤ãĥ¤
    -0.08
     Torrent
    -0.08
    çĩķ
    -0.08
     legacy
    -0.08
     ÑĤабли
    -0.08
     Gad
    -0.08
     Juda
    -0.08
    POSITIVE LOGITS
     branch
    0.24
     branches
    0.19
     area
    0.19
     Branch
    0.18
    branch
    0.17
     field
    0.17
     technology
    0.17
    Branch
    0.16
    area
    0.16
     discipline
    0.16
    Activations Density 0.166%

    No Known Activations