Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65352
    Prev
    Next
    INDEX
    Explanations

    Attention as a Lift

    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
    ignum
    -0.10
     vis
    -0.10
     Conway
    -0.10
     Taj
    -0.10
     spatial
    -0.09
    :::::
    -0.09
     Concert
    -0.09
     Mell
    -0.09
     Desk
    -0.09
     hab
    -0.09
    POSITIVE LOGITS
     man
    0.17
     fol
    0.17
     charts
    0.16
     bundle
    0.15
    bundle
    0.15
    Charts
    0.15
    fol
    0.14
     jets
    0.14
     Lie
    0.13
     Charts
    0.13
    Activations Density 0.034%

    No Known Activations