© 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. 49270
    Prev
    Next
    INDEX
    Explanations

    sequential numbers followed by a dot

    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
    irie
    -0.09
     ----------------------------------------------------------------------\n
    -0.08
     quart
    -0.08
    otos
    -0.08
    ards
    -0.08
    itol
    -0.08
    071
    -0.08
    맹
    -0.07
    eko
    -0.07
     Place
    -0.07
    POSITIVE LOGITS
    0.10
    achi
    0.09
    arella
    0.09
    tring
    0.08
     Fletcher
    0.08
     âĨĴ\n\n
    0.08
     opr
    0.08
    ther
    0.08
     Beaver
    0.08
    ｨ
    0.08
    Activations Density 0.061%

    No Known Activations