© 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. 29575
    Prev
    Next
    INDEX
    Explanations

    be automated or not easily

    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
     unus
    -0.12
     usable
    -0.11
    usable
    -0.11
    EGA
    -0.10
    _used
    -0.10
     USED
    -0.10
    used
    -0.09
    USED
    -0.09
    åŃĹå¹ķ
    -0.09
     stip
    -0.09
    POSITIVE LOGITS
     candidates
    0.17
     benef
    0.16
     benefit
    0.16
     candidate
    0.16
    éĢĤ
    0.15
     benefited
    0.15
     Benefit
    0.15
     ripe
    0.14
     served
    0.13
     prime
    0.13
    Activations Density 0.170%

    No Known Activations