© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30372
    Prev
    Next
    INDEX
    Explanations

    's not, way for, will be

    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
     seper
    -0.11
     occured
    -0.10
     embar
    -0.10
     irresist
    -0.09
    oka
    -0.09
    elen
    -0.09
    INCT
    -0.09
     corres
    -0.09
     prive
    -0.09
     Morrow
    -0.09
    POSITIVE LOGITS
    estruct
    0.10
     âĨij
    0.09
    exemple
    0.09
    ··
    0.09
    ighton
    0.09
     ë¸
    0.09
     scape
    0.09
     rapp
    0.09
    awe
    0.09
    ï¼¹
    0.09
    Activations Density 0.051%

    No Known Activations