© 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. 53685
    Prev
    Next
    INDEX
    Explanations

    time to complete action

    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
     continued
    -0.09
     tục
    -0.09
     incom
    -0.09
     endings
    -0.09
     influx
    -0.09
     prolonged
    -0.09
    anness
    -0.09
    ucs
    -0.09
    stance
    -0.08
     stretch
    -0.08
    POSITIVE LOGITS
     complete
    0.17
     reach
    0.14
     fully
    0.14
     completion
    0.14
     completely
    0.14
    å®ĮæĪIJ
    0.13
    å®Įåħ¨
    0.12
    complete
    0.12
     hoÃłn
    0.12
     Completion
    0.12
    Activations Density 0.069%

    No Known Activations