© 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. 23717
    Prev
    Next
    INDEX
    Explanations

    `note` or `however` indicating follow-up

    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
    jumbotron
    -0.08
    CDATA
    -0.08
     ï½Į
    -0.08
     conce
    -0.08
    PFN
    -0.07
     overhe
    -0.07
    thus
    -0.07
    åĽłæѤ
    -0.07
    SKU
    -0.07
     cân
    -0.07
    POSITIVE LOGITS
     note
    0.11
     However
    0.11
    Note
    0.11
    However
    0.10
     Note
    0.10
    误
    0.09
    note
    0.09
     however
    0.09
    -note
    0.09
     again
    0.09
    Activations Density 0.001%

    No Known Activations