© 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. 14459
    Prev
    Next
    INDEX
    Explanations

    record levels

    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
     Sphere
    -0.09
    iosa
    -0.09
    ceph
    -0.08
     sne
    -0.08
    uan
    -0.08
     Tot
    -0.08
    ataka
    -0.08
     Jas
    -0.08
    zcze
    -0.08
    bia
    -0.08
    POSITIVE LOGITS
     record
    0.19
     levels
    0.18
     nad
    0.16
     ATH
    0.16
     Record
    0.16
     hit
    0.14
     historical
    0.14
     Levels
    0.14
     reached
    0.13
    Levels
    0.13
    Activations Density 0.073%

    No Known Activations