© 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. 4761
    Prev
    Next
    INDEX
    Explanations

    then allowing

    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
     졸
    -0.08
    asInstanceOf
    -0.08
     unused
    -0.08
     inform
    -0.08
     allegiance
    -0.08
    iyat
    -0.08
     persist
    -0.08
    igor
    -0.07
     ing
    -0.07
     Accountability
    -0.07
    POSITIVE LOGITS
     allow
    0.48
    allow
    0.43
     allowing
    0.42
     Allow
    0.42
    Allow
    0.40
     letting
    0.40
     let
    0.39
     allows
    0.38
     leave
    0.36
     ALLOW
    0.35
    Activations Density 0.115%

    No Known Activations