© 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. 49004
    Prev
    Next
    INDEX
    Explanations

    challenges including lack

    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
    ä¼ĺåĬ¿
    -0.10
     incon
    -0.10
     sav
    -0.10
     strengths
    -0.09
     playing
    -0.09
    åĬ©
    -0.09
     use
    -0.09
    ruz
    -0.08
    airo
    -0.08
    icit
    -0.08
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.14
    æī¾åĪ°
    0.13
     how
    0.11
     lack
    0.11
    bal
    0.11
     guarantee
    0.11
    Maint
    0.11
    finding
    0.11
     porr
    0.11
     finding
    0.11
    Activations Density 0.111%

    No Known Activations