© 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. 20273
    Prev
    Next
    INDEX
    Explanations

    docker build context

    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
     Rating
    -0.09
    ops
    -0.08
    anta
    -0.08
     Santa
    -0.08
    DataManager
    -0.08
    Santa
    -0.08
    eria
    -0.08
     Harden
    -0.08
    avage
    -0.08
    âĶIJ
    -0.08
    POSITIVE LOGITS
    ---</
    0.10
    ɵ
    0.09
    htdocs
    0.09
    ľĺ
    0.08
    507
    0.08
     çĶŁåij½åij¨æľŁåĩ½æķ°
    0.08
    searchModel
    0.08
    ----</
    0.08
    uzzi
    0.08
     Trick
    0.08
    Activations Density 0.047%

    No Known Activations