© 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. 12794
    Prev
    Next
    INDEX
    Explanations

    kinds of things

    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
     pec
    -0.11
     concerned
    -0.10
    mentioned
    -0.10
    $MESS
    -0.10
     salopes
    -0.10
     remaining
    -0.09
    anvas
    -0.09
    CRET
    -0.09
     academia
    -0.09
    #aa
    -0.09
    POSITIVE LOGITS
     sorts
    0.23
     kinds
    0.19
     sort
    0.15
     Sort
    0.12
     surpr
    0.10
    sort
    0.10
     SORT
    0.09
    Sort
    0.09
     types
    0.09
    uma
    0.09
    Activations Density 0.059%

    No Known Activations