© 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. 22797
    Prev
    Next
    INDEX
    Explanations

    how to comment

    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
    å¶
    -0.10
    baugh
    -0.09
    -Semit
    -0.09
    ording
    -0.09
     Schultz
    -0.09
    anner
    -0.09
     Ner
    -0.08
    eah
    -0.08
    çĻ
    -0.08
    edx
    -0.08
    POSITIVE LOGITS
    aries
    0.25
    ary
    0.19
    aires
    0.18
    ators
    0.18
    aire
    0.15
    (comment
    0.15
    ator
    0.14
    .Comment
    0.14
    luv
    0.14
    ARY
    0.14
    Activations Density 0.030%

    No Known Activations