© 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. 62385
    Prev
    Next
    INDEX
    Explanations

    ensure cost basis reflects security 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
    ارش
    -0.10
     tro
    -0.09
     carefully
    -0.09
     collaps
    -0.08
     finishing
    -0.08
     rewrite
    -0.08
    ÏĦÏģ
    -0.08
    stor
    -0.08
    ÑıÑĤелÑĮ
    -0.08
     Erg
    -0.08
    POSITIVE LOGITS
     remain
    0.19
     remains
    0.19
     stay
    0.18
    remain
    0.17
     remained
    0.17
     stays
    0.17
     continued
    0.17
    ä¿ĿæĮģ
    0.15
     continue
    0.15
     keep
    0.15
    Activations Density 0.050%

    No Known Activations