© 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. 60275
    Prev
    Next
    INDEX
    Explanations

    clauses ending in punctuation

    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
    æĪIJ为
    -0.11
     themselves
    -0.11
     Py
    -0.10
    .isNullOrEmpty
    -0.09
    æĪIJçĤº
    -0.09
     Killing
    -0.09
    esor
    -0.09
    ä½ľä¸º
    -0.09
    Py
    -0.09
    &R
    -0.09
    POSITIVE LOGITS
     able
    0.12
    inaire
    0.11
     ready
    0.10
    alm
    0.10
     feared
    0.09
     constantly
    0.09
    afs
    0.09
    aring
    0.09
     presente
    0.09
     always
    0.09
    Activations Density 0.101%

    No Known Activations