© 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. 19828
    Prev
    Next
    INDEX
    Explanations

    tall figures and trees

    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
    IGHL
    -0.10
    urovision
    -0.10
    dll
    -0.09
    YYY
    -0.09
    _LVL
    -0.09
    -looking
    -0.09
    GES
    -0.09
    chten
    -0.08
    astically
    -0.08
    solete
    -0.08
    POSITIVE LOGITS
    ented
    0.19
    ahas
    0.16
    ied
    0.15
     stature
    0.14
     tales
    0.14
     Tales
    0.13
    -standing
    0.12
    ents
    0.12
     ceilings
    0.12
    grass
    0.12
    Activations Density 0.031%

    No Known Activations