© 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. 59406
    Prev
    Next
    INDEX
    Explanations

    assist with users

    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
     =
    -0.09
     Broadway
    -0.09
     Hint
    -0.08
    inha
    -0.08
    a
    -0.08
     prer
    -0.08
     arcane
    -0.08
    how
    -0.08
    ourg
    -0.08
     unsuccessfully
    -0.08
    POSITIVE LOGITS
    ive
    0.16
     users
    0.13
    çĶ¨æĪ·
    0.12
    ively
    0.12
     user
    0.10
     użytk
    0.10
    ivec
    0.10
     Äijỡ
    0.10
    ência
    0.10
    iveness
    0.10
    Activations Density 0.030%

    No Known Activations