© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29794
    Prev
    Next
    INDEX
    Explanations

    inhibiting enzyme activity

    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
     unarmed
    -0.10
    çĥĪ
    -0.09
     gridColumn
    -0.09
     Mara
    -0.09
     Ens
    -0.09
     McInt
    -0.08
     Regulation
    -0.08
     prob
    -0.08
     dara
    -0.08
     safezone
    -0.08
    POSITIVE LOGITS
     key
    0.12
     targets
    0.12
     activity
    0.12
     Counsel
    0.10
     enemy
    0.10
     abnormal
    0.10
     Targets
    0.10
     function
    0.10
     action
    0.10
    targets
    0.09
    Activations Density 0.038%

    No Known Activations