© 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. 39994
    Prev
    Next
    INDEX
    Explanations

    CE mark or Acecarbromal instructions

    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
    ICY
    -0.10
     haz
    -0.10
    ndef
    -0.09
    ollen
    -0.09
     Carnegie
    -0.09
    mand
    -0.09
    osc
    -0.09
    sembly
    -0.09
     Bris
    -0.09
    ë²Ķ
    -0.09
    POSITIVE LOGITS
    stral
    0.13
    ILING
    0.11
    iling
    0.10
    ÄŁiz
    0.10
    ption
    0.10
    usters
    0.10
    ingen
    0.10
    ownik
    0.10
    ce
    0.10
    eper
    0.10
    Activations Density 0.056%

    No Known Activations