© 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. 21
    Prev
    Next
    INDEX
    Explanations

    medium and long term

    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
    .weixin
    -0.09
    erah
    -0.09
    ¶Į
    -0.09
    Isl
    -0.09
    .gdx
    -0.09
    _PCM
    -0.09
    ighbor
    -0.08
     ведÑĮ
    -0.08
     ï½Ģ
    -0.08
    Äł
    -0.08
    POSITIVE LOGITS
    /o
    0.24
    /or
    0.22
    /of
    0.15
    ÑĢониÑĩеÑģ
    0.15
    /OR
    0.13
    ymology
    0.13
    мовÑĸÑĢ
    0.12
    /
    0.12
    oes
    0.12
    jet
    0.12
    Activations Density 0.141%

    No Known Activations