© 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. 60534
    Prev
    Next
    INDEX
    Explanations

    stop

    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
    racak
    -0.10
     shrinking
    -0.09
     disappearance
    -0.09
    _blocking
    -0.09
     stripped
    -0.09
     reopened
    -0.09
    onga
    -0.09
     forfe
    -0.09
    ModelState
    -0.09
    Ø·ÙĨ
    -0.09
    POSITIVE LOGITS
     stop
    0.65
     stopped
    0.59
    åģľæŃ¢
    0.55
     Stop
    0.55
     stopping
    0.53
     stops
    0.52
    stop
    0.49
    Stop
    0.49
     STOP
    0.49
    .stop
    0.47
    Activations Density 0.158%

    No Known Activations