© 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. 51670
    Prev
    Next
    INDEX
    Explanations

    key-value pairs and structured data

    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
    nds
    -0.10
    egers
    -0.09
     Dawn
    -0.09
    uD
    -0.08
     conscient
    -0.08
     Hed
    -0.08
    vero
    -0.08
    \č\n
    -0.08
    ToPoint
    -0.08
     heter
    -0.08
    POSITIVE LOGITS
    AGMA
    0.08
    HasBeenSet
    0.08
    xmm
    0.08
    dispose
    0.08
    езÑĥлÑĮÑĤ
    0.08
    ë§Ŀ
    0.08
    /goto
    0.08
    lik
    0.08
    (WIN
    0.08
     grate
    0.08
    Activations Density 0.074%

    No Known Activations