© 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. 57808
    Prev
    Next
    INDEX
    Explanations

    past tense state descriptions

    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
     ÙĬÙĥÙĪÙĨ
    -0.12
    ãģłãĤįãģĨ
    -0.11
    apa
    -0.10
    äºĨä¸Ģ
    -0.10
    .sy
    -0.09
    thed
    -0.09
     Liqu
    -0.08
    AspNet
    -0.08
    odo
    -0.08
     تÙĥÙĪÙĨ
    -0.08
    POSITIVE LOGITS
    nt
    0.37
    /is
    0.25
    nts
    0.19
    /am
    0.17
    NT
    0.17
    abi
    0.16
    htub
    0.16
    was
    0.15
    ÅĽmy
    0.15
     originally
    0.15
    Activations Density 0.119%

    No Known Activations