© 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. 49496
    Prev
    Next
    INDEX
    Explanations

    detection, detritus, detail, DETR

    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
    icum
    -0.12
     tire
    -0.09
    acious
    -0.09
    âī§
    -0.09
    ä¸īä¸ī
    -0.09
    quist
    -0.09
     Gregg
    -0.09
    RTOS
    -0.08
    arks
    -0.08
    ENCIL
    -0.08
    POSITIVE LOGITS
     det
    0.17
    (det
    0.13
    lef
    0.13
    det
    0.12
    -det
    0.12
     Det
    0.12
    ectors
    0.12
     деÑĤ
    0.12
     DET
    0.12
    .det
    0.11
    Activations Density 0.026%

    No Known Activations