© 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. 50318
    Prev
    Next
    INDEX
    Explanations

    evaluating statement intent

    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
    enames
    -0.09
     bow
    -0.09
    nop
    -0.08
     spelling
    -0.08
     Reality
    -0.08
     reality
    -0.08
     Fortress
    -0.08
     bows
    -0.08
    ocz
    -0.08
     stalking
    -0.08
    POSITIVE LOGITS
     requested
    0.17
     request
    0.17
     asked
    0.15
     example
    0.13
     instruction
    0.13
     completion
    0.12
     instructions
    0.12
     scenario
    0.12
    (request
    0.11
     examples
    0.11
    Activations Density 0.161%

    No Known Activations