© 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. 12925
    Prev
    Next
    INDEX
    Explanations

    as ischemic

    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
     gust
    -0.10
     glands
    -0.10
     guts
    -0.10
     disap
    -0.10
     cervical
    -0.09
     deg
    -0.09
     Punch
    -0.09
     sp
    -0.09
     ast
    -0.09
    zik
    -0.09
    POSITIVE LOGITS
     ven
    0.26
     Ven
    0.24
    Ven
    0.22
     emb
    0.22
    ven
    0.19
     throm
    0.18
     leg
    0.18
     Pul
    0.17
     vein
    0.17
     clot
    0.16
    Activations Density 0.041%

    No Known Activations