© 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. 33213
    Prev
    Next
    INDEX
    Explanations

    significance or necessity

    np_acts-logits-general · gemini-2.5-flash-lite

    clauses that introduce important qualifications, conditions, or concerns that need to be addressed.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @yooniel31
    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
    ï½Ń
    -0.10
     happens
    -0.09
     Kaw
    -0.09
     guilty
    -0.09
     rightfully
    -0.09
    STRU
    -0.09
    867
    -0.09
    outil
    -0.08
    adow
    -0.08
    apgolly
    -0.08
    POSITIVE LOGITS
     worth
    0.33
     requires
    0.30
     warrant
    0.30
     require
    0.29
     needs
    0.28
     Requires
    0.27
    éľĢè¦ģ
    0.27
     Worth
    0.26
     WARRANT
    0.25
    worth
    0.24
    Activations Density 0.239%

    No Known Activations