© 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. 51426
    Prev
    Next
    INDEX
    Explanations

    owner's permission

    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
     Guest
    -0.10
     detr
    -0.10
    Reviewer
    -0.10
    hung
    -0.10
     learners
    -0.10
     Lear
    -0.10
     callers
    -0.09
     debido
    -0.09
     vp
    -0.09
    åĭĴ
    -0.09
    POSITIVE LOGITS
     owners
    0.69
     owner
    0.68
     Owners
    0.54
    owner
    0.53
     Owner
    0.52
    owners
    0.50
    Owner
    0.49
    Owners
    0.47
    -owner
    0.46
    .owner
    0.45
    Activations Density 0.189%

    No Known Activations