© 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. 2581
    Prev
    Next
    INDEX
    Explanations

    expertise in

    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
    er
    -0.13
    ning
    -0.10
    ces
    -0.10
     minded
    -0.10
    OTO
    -0.09
    amble
    -0.09
    ading
    -0.09
    deb
    -0.09
    eru
    -0.09
    fsp
    -0.08
    POSITIVE LOGITS
    ise
    0.17
    ISE
    0.13
    ises
    0.12
    ly
    0.11
     knowledge
    0.11
    knowledge
    0.11
    isen
    0.10
    çŁ¥è¯Ĩ
    0.10
    ORMAL
    0.10
     areas
    0.10
    Activations Density 0.011%

    No Known Activations