© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 38275
    Prev
    Next
    INDEX
    Explanations

    good or bad descriptions

    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
    Negative Logits
    joint
    -0.09
     Pek
    -0.09
     ener
    -0.09
    artisan
    -0.09
     Caller
    -0.09
    erty
    -0.08
    aison
    -0.08
     Neville
    -0.08
     Cousins
    -0.08
    uct
    -0.08
    POSITIVE LOGITS
     person
    0.21
     citizen
    0.18
     citizens
    0.15
     listener
    0.14
     human
    0.14
     Person
    0.13
     listeners
    0.13
     friend
    0.13
    cit
    0.12
     daughter
    0.12
    Activations Density 0.079%

    No Known Activations