© 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. 26354
    Prev
    Next
    INDEX
    Explanations

    even in difficult situations

    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
     various
    -0.09
    oler
    -0.09
     easiest
    -0.08
     discretion
    -0.08
    arily
    -0.08
     both
    -0.08
    olds
    -0.08
    hatt
    -0.08
    kate
    -0.08
    ı
    -0.08
    POSITIVE LOGITS
     ÑģамÑĭÑħ
    0.15
    -handed
    0.14
     smallest
    0.14
     seemingly
    0.13
    æľĢ
    0.13
     though
    0.11
     remot
    0.11
     something
    0.11
    -number
    0.10
    éĤ£äºĽ
    0.10
    Activations Density 0.035%

    No Known Activations