© 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. 60952
    Prev
    Next
    INDEX
    Explanations

    discover realities and debunk myths

    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
    Hints
    -0.12
     critiques
    -0.11
    :;\n
    -0.10
    ainen
    -0.09
    "crypto
    -0.09
     criticism
    -0.09
    _COND
    -0.09
     disagreed
    -0.09
     Curl
    -0.09
     fort
    -0.09
    POSITIVE LOGITS
     disp
    0.30
    disp
    0.24
     cleared
    0.23
     myth
    0.22
    æ¾
    0.22
     clears
    0.21
     clearing
    0.21
     Myth
    0.21
     truth
    0.21
     Disp
    0.21
    Activations Density 0.179%

    No Known Activations