© 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. 16656
    Prev
    Next
    INDEX
    Explanations

    must then state a syllogism

    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
    ÅĽcie
    -0.09
     carp
    -0.09
    ecs
    -0.09
     releg
    -0.08
    trl
    -0.08
     ç¬
    -0.08
     Vern
    -0.08
     Tart
    -0.08
    antha
    -0.08
    _exempt
    -0.08
    POSITIVE LOGITS
     stump
    0.12
     continuation
    0.11
     contributions
    0.11
     word
    0.11
     challenge
    0.10
     challenged
    0.10
     chain
    0.10
    è½®
    0.10
    ictionary
    0.10
     Chain
    0.10
    Activations Density 0.143%

    No Known Activations