© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 32135
    Prev
    Next
    INDEX
    Explanations

    creative writing and expression

    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
    /create
    -0.15
    OrCreate
    -0.12
    Created
    -0.10
     creativity
    -0.10
     created
    -0.10
     Created
    -0.10
     creates
    -0.10
    _CREATE
    -0.10
    _created
    -0.10
    Create
    -0.10
    POSITIVE LOGITS
     Commons
    0.19
     juices
    0.16
     commons
    0.16
    -common
    0.14
     outlets
    0.14
     outlet
    0.14
    commons
    0.13
     license
    0.13
    -destruct
    0.13
     writing
    0.13
    Activations Density 0.021%

    No Known Activations