© 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. 46955
    Prev
    Next
    INDEX
    Explanations

    rather see than be

    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
     enough
    -0.10
     basically
    -0.10
    igin
    -0.09
    sg
    -0.09
    imar
    -0.09
    AMP
    -0.09
    yon
    -0.09
     )\n\n\n\n\n\n\n\n
    -0.09
    452
    -0.09
    eme
    -0.08
    POSITIVE LOGITS
     than
    0.30
    than
    0.23
     niż
    0.22
     än
    0.21
     než
    0.21
     THAN
    0.20
    _than
    0.20
     Than
    0.19
    Than
    0.19
    -than
    0.18
    Activations Density 0.075%

    No Known Activations