© 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. 62235
    Prev
    Next
    INDEX
    Explanations

    appropriate to add

    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
     clinically
    -0.11
     Regulation
    -0.11
     injected
    -0.10
     prognosis
    -0.10
     ing
    -0.10
     injecting
    -0.09
     regulation
    -0.09
     prere
    -0.09
     injection
    -0.09
     clinical
    -0.09
    POSITIVE LOGITS
     tit
    0.14
     agents
    0.14
     Tit
    0.12
     backbone
    0.12
     Emp
    0.12
     empirical
    0.12
    agents
    0.12
    tit
    0.12
    Tit
    0.12
     taper
    0.11
    Activations Density 0.074%

    No Known Activations