© 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. 21020
    Prev
    Next
    INDEX
    Explanations

    goals and objectives

    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
     goals
    -0.17
     goal
    -0.17
     Goals
    -0.15
    _goals
    -0.14
    _goal
    -0.14
    -goal
    -0.14
    goals
    -0.13
     ÑĨелÑĮ
    -0.13
    Goals
    -0.13
     gates
    -0.13
    POSITIVE LOGITS
    obj
    0.11
     secondary
    0.10
    ä¸ĺ
    0.10
     Means
    0.10
    į°
    0.09
     surplus
    0.09
    lname
    0.09
     obj
    0.09
     Secondary
    0.09
    erif
    0.09
    Activations Density 0.091%

    No Known Activations