© 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. 12736
    Prev
    Next
    INDEX
    Explanations

    names of places

    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
    owie
    -0.10
     Apollo
    -0.09
    ancode
    -0.09
    ovah
    -0.09
     abras
    -0.09
    lander
    -0.09
     Pager
    -0.08
    Apollo
    -0.08
    AXB
    -0.08
    ostringstream
    -0.08
    POSITIVE LOGITS
     Sector
    0.14
    Sector
    0.12
     sector
    0.11
     Radi
    0.11
     Area
    0.11
     Mount
    0.10
    /Area
    0.10
     Paw
    0.10
     fictional
    0.10
     Lover
    0.10
    Activations Density 0.196%

    No Known Activations