© 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. 383
    Prev
    Next
    INDEX
    Explanations

    raw material ingredient component

    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
    INAL
    -0.09
    obus
    -0.09
     foods
    -0.08
     Foods
    -0.08
    chestra
    -0.08
    åĪ©çĶ¨
    -0.08
     forks
    -0.08
    íĥĦ
    -0.08
     Mechanics
    -0.08
     inj
    -0.08
    POSITIVE LOGITS
     ingredient
    0.15
     component
    0.14
     raw
    0.12
    ingredient
    0.12
    component
    0.12
     components
    0.12
     modifier
    0.12
     impro
    0.12
     componente
    0.12
    åĬ©
    0.12
    Activations Density 0.019%

    No Known Activations