© 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. 54977
    Prev
    Next
    INDEX
    Explanations

    risks and consequences

    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
    ä¸ĢäºĽ
    -0.15
    ä¸Ģç§į
    -0.14
    ä¸ĢåĢĭ
    -0.12
    åŃIJä¾Ľ
    -0.11
    ä¸ĢçĤ¹
    -0.11
    istrovstvÃŃ
    -0.10
    ä¸Ģ
    -0.10
    lectic
    -0.09
    ä¸Ģ人
    -0.09
    uder
    -0.09
    POSITIVE LOGITS
     such
    0.15
    such
    0.14
    course
    0.13
    Such
    0.12
     Such
    0.12
     continued
    0.12
     sorts
    0.11
     suche
    0.11
     Actions
    0.10
     SUCH
    0.10
    Activations Density 0.044%

    No Known Activations