© 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. 37140
    Prev
    Next
    INDEX
    Explanations

    tools and objectives

    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
    ｧ
    -0.10
    czy
    -0.08
     Lt
    -0.08
    _blend
    -0.08
     æĢ
    -0.08
    æħ
    -0.08
    cko
    -0.08
     поба
    -0.08
    rote
    -0.08
    ongo
    -0.08
    POSITIVE LOGITS
     aim
    0.30
     aims
    0.27
    aim
    0.23
    aims
    0.22
     hope
    0.22
     seeks
    0.21
     goal
    0.20
    æĹ
    0.19
     hoped
    0.19
     Aim
    0.18
    Activations Density 0.122%

    No Known Activations