© 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. 27494
    Prev
    Next
    INDEX
    Explanations

    conditions or time points

    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
    amac
    -0.09
     Hend
    -0.09
     sublicense
    -0.09
    erras
    -0.09
    ynamo
    -0.09
    ALAR
    -0.09
    raq
    -0.08
     sokak
    -0.08
    DBG
    -0.08
     arrows
    -0.08
    POSITIVE LOGITS
     treatment
    0.16
     runs
    0.15
     across
    0.15
     conditions
    0.14
     condition
    0.14
     treatments
    0.13
     run
    0.13
     Runs
    0.13
     trials
    0.13
     considered
    0.13
    Activations Density 0.144%

    No Known Activations