© 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. 55226
    Prev
    Next
    INDEX
    Explanations

    Arisaema heterophyllum seed

    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
     Branch
    -0.12
     branch
    -0.11
    /Branch
    -0.10
    æŀĿ
    -0.10
     Bloss
    -0.10
     bloss
    -0.10
     Lair
    -0.10
     fruit
    -0.10
    fruit
    -0.10
    Branch
    -0.10
    POSITIVE LOGITS
     bulbs
    0.27
     bulb
    0.25
     Bul
    0.17
    bul
    0.16
     underground
    0.15
     narciss
    0.15
    ÑĤÑİ
    0.14
     tub
    0.13
     Underground
    0.13
     tul
    0.13
    Activations Density 0.043%

    No Known Activations