© 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. 35764
    Prev
    Next
    INDEX
    Explanations

    not followed by words like any, for, as

    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
     plenty
    -0.11
    atham
    -0.10
    itar
    -0.10
     Merr
    -0.09
     Plenty
    -0.09
    wald
    -0.09
     Als
    -0.09
    彡
    -0.09
    undi
    -0.08
    avar
    -0.08
    POSITIVE LOGITS
     tolik
    0.28
    éĤ£ä¹Ī
    0.25
     as
    0.25
     nearly
    0.25
     tão
    0.24
     à¤ĩतन
    0.24
     quite
    0.23
     aussi
    0.21
     same
    0.20
    å°½
    0.20
    Activations Density 0.073%

    No Known Activations