© 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. 52138
    Prev
    Next
    INDEX
    Explanations

    however, contrast, phrases

    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
    IFS
    -0.10
     Pil
    -0.10
     Hv
    -0.09
    ros
    -0.09
     pha
    -0.09
    GR
    -0.09
     sic
    -0.09
     Sap
    -0.08
    _INTERRUPT
    -0.08
    _scr
    -0.08
    POSITIVE LOGITS
    ï¿£ï½Ģ
    0.09
    æ¦
    0.09
    :::::::::::::
    0.09
     McCorm
    0.09
    essler
    0.09
    ucursal
    0.09
    783
    0.09
    iker
    0.08
    ipo
    0.08
    877
    0.08
    Activations Density 0.195%

    No Known Activations