© 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. 58758
    Prev
    Next
    INDEX
    Explanations

    adverbs describing correctness/consistency

    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
    SURE
    -0.09
    -ending
    -0.09
     Madden
    -0.08
    odo
    -0.08
    abo
    -0.08
    COMPARE
    -0.08
    dge
    -0.08
    ãĤ¤ãĥĦ
    -0.08
    ouver
    -0.08
     CrossAxisAlignment
    -0.08
    POSITIVE LOGITS
     speaking
    0.13
    -speaking
    0.13
     correct
    0.12
     consistent
    0.12
     Speaking
    0.10
     challenged
    0.10
    uw
    0.10
     consistency
    0.10
     sound
    0.10
    åķ
    0.10
    Activations Density 0.007%

    No Known Activations