© 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. 13235
    Prev
    Next
    INDEX
    Explanations

    driven by desire or intention

    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
    KeyType
    -0.10
    usal
    -0.09
    .tem
    -0.09
    _fence
    -0.09
    odiac
    -0.09
    ventus
    -0.09
     responsibilities
    -0.09
     Responsibilities
    -0.08
     ãĥ
    -0.08
    FullPath
    -0.08
    POSITIVE LOGITS
    mot
    0.25
     motivated
    0.23
    Mot
    0.22
     моÑĤ
    0.21
     motivation
    0.21
     Mot
    0.21
     motive
    0.21
     motivations
    0.20
     motives
    0.20
     acting
    0.19
    Activations Density 0.110%

    No Known Activations