© 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. 29790
    Prev
    Next
    INDEX
    Explanations

    that output, a story, "hell", each release, the generation, adult meals, NVIDIA NAME

    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
    ÑĮко
    -0.08
    ¶Į
    -0.07
    _marshall
    -0.07
    OLVE
    -0.07
    âĨ
    -0.07
    <!--<
    -0.07
    ¯u
    -0.07
    _vlog
    -0.07
     UIResponder
    -0.07
    ÅĻez
    -0.07
    POSITIVE LOGITS
    ëį°ìĿ´íĬ¸
    0.10
    íĨłíĨł
    0.07
    rors
    0.07
     yüksel
    0.07
    dealloc
    0.07
     Hank
    0.07
     BÄ°L
    0.06
     Ä°mpar
    0.06
    "w
    0.06
     ìĿ´ìĸ´
    0.06
    Activations Density 0.661%

    No Known Activations