© 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. 34241
    Prev
    Next
    INDEX
    Explanations

    many followed by time or description

    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
    ney
    -0.10
    ilon
    -0.10
    halb
    -0.09
    arges
    -0.09
    iller
    -0.09
    cs
    -0.09
    ses
    -0.09
     continents
    -0.09
     Wayback
    -0.08
    iti
    -0.08
    POSITIVE LOGITS
    ToMany
    0.23
    fold
    0.22
    -many
    0.21
     different
    0.19
    -sided
    0.18
    yyy
    0.16
    /all
    0.16
    different
    0.14
    yyyy
    0.14
    atta
    0.14
    Activations Density 0.049%

    No Known Activations