© 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. 24524
    Prev
    Next
    INDEX
    Explanations

    project proposal plan details

    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
    ious
    -0.09
    lass
    -0.09
    itti
    -0.09
     Satisfaction
    -0.08
    ehler
    -0.08
    asca
    -0.08
    inventory
    -0.08
     Summon
    -0.08
     Invent
    -0.08
     invent
    -0.08
    POSITIVE LOGITS
     proposal
    0.29
     project
    0.21
     Proposal
    0.21
     propos
    0.21
     proposed
    0.21
    Proposal
    0.20
    proposal
    0.19
     proposals
    0.19
     propose
    0.17
     proposing
    0.16
    Activations Density 0.071%

    No Known Activations