© 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. 63526
    Prev
    Next
    INDEX
    Explanations

    past tense actions and states

    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
    able
    -0.14
    ingly
    -0.13
    edException
    -0.12
    ä¸Ģ次
    -0.11
    eds
    -0.11
    493
    -0.11
    edback
    -0.11
    ings
    -0.11
    ised
    -0.10
    ables
    -0.10
    POSITIVE LOGITS
    nt
    0.20
    /is
    0.19
     бÑĭ
    0.18
    /generated
    0.18
    /cop
    0.17
    s
    0.16
     jsem
    0.16
    ness
    0.16
    /shared
    0.15
    ãĤĬ
    0.15
    Activations Density 0.242%

    No Known Activations