© 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. 23851
    Prev
    Next
    INDEX
    Explanations

    top, popular, best

    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
    åħ¸
    -0.11
     Kear
    -0.09
    orph
    -0.08
    Gu
    -0.08
    054
    -0.08
    WithTag
    -0.08
    RACT
    -0.08
    ovo
    -0.08
    ãĥ³ãĥĨãĤ£
    -0.08
    iger
    -0.08
    POSITIVE LOGITS
     top
    0.27
     popular
    0.23
    popular
    0.19
     highly
    0.17
     Popular
    0.16
    top
    0.16
     Highly
    0.16
     ÑĤоп
    0.15
     Top
    0.15
     popularity
    0.15
    Activations Density 0.180%

    No Known Activations