© 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. 58346
    Prev
    Next
    INDEX
    Explanations

    edge of

    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
    /edit
    -0.11
    ollen
    -0.11
    /Edit
    -0.10
    doch
    -0.10
     Ober
    -0.09
    ÏĤ
    -0.09
    soever
    -0.09
    ly
    -0.09
    neck
    -0.09
    shape
    -0.09
    POSITIVE LOGITS
    ç¼ĺ
    0.22
    combe
    0.17
    hog
    0.16
    =edge
    0.16
    (edge
    0.14
    -edge
    0.14
    hill
    0.13
    éĻħ
    0.13
    [edge
    0.12
    ç·
    0.12
    Activations Density 0.023%

    No Known Activations