© 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. 26267
    Prev
    Next
    INDEX
    Explanations

    introduces descriptive clauses

    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
     ìŀĪëĭ¤ê³ł
    -0.09
    594
    -0.09
    ese
    -0.08
    complete
    -0.08
     Bek
    -0.08
     complete
    -0.08
     Lor
    -0.08
    iece
    -0.08
     washed
    -0.08
     Kre
    -0.08
    POSITIVE LOGITS
     which
    0.32
    which
    0.28
     WHICH
    0.22
     Which
    0.20
    Which
    0.20
    è¿Ļæĺ¯
    0.18
     à¸ĭ
    0.18
     typical
    0.18
    (which
    0.16
    typ
    0.15
    Activations Density 0.198%

    No Known Activations