© 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. 56692
    Prev
    Next
    INDEX
    Explanations

    temporary state

    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
     Permanent
    -0.10
     foregoing
    -0.09
     permanently
    -0.09
    quin
    -0.09
     Forever
    -0.09
     ï¾Ħ
    -0.09
     Masc
    -0.08
    angi
    -0.08
     vaguely
    -0.08
    rado
    -0.08
    POSITIVE LOGITS
    æļĤ
    0.35
    brief
    0.31
     temporary
    0.29
     brief
    0.29
    Brief
    0.27
     ìŀł
    0.26
     Brief
    0.25
     tạm
    0.25
    tmp
    0.23
     нен
    0.23
    Activations Density 0.198%

    No Known Activations