© 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. 16889
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    åħ¥
    -0.10
    omp
    -0.10
    956
    -0.10
     inward
    -0.10
    owl
    -0.10
     peeled
    -0.09
     McKay
    -0.09
     Pub
    -0.08
     inlet
    -0.08
     [|
    -0.08
    POSITIVE LOGITS
    åĩºæĿ¥
    0.44
     exit
    0.41
     out
    0.38
     вÑĭÑħод
    0.35
     exiting
    0.34
     exits
    0.33
     Exit
    0.32
     exited
    0.32
    exit
    0.31
    خرج
    0.31
    Activations Density 0.178%

    No Known Activations