© 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. 15084
    Prev
    Next
    INDEX
    Explanations

    otologist

    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
    oon
    -0.11
    ois
    -0.11
    odge
    -0.11
    ox
    -0.10
    à¹Ĥà¸Ĭ
    -0.10
    /object
    -0.10
    och
    -0.10
     Kv
    -0.10
    oir
    -0.10
    oons
    -0.10
    POSITIVE LOGITS
    aku
    0.13
    awa
    0.12
    entic
    0.11
    ensibly
    0.11
    ting
    0.11
    obre
    0.11
    sw
    0.11
    to
    0.11
    iginal
    0.11
    THON
    0.10
    Activations Density 0.025%

    No Known Activations