© 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. 57887
    Prev
    Next
    INDEX
    Explanations

    is used; it states; it is

    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
    ãĥ»ãĥ»ãĥ»\n\n
    -0.10
    (æ°´
    -0.08
    âĶ´
    -0.08
    <|begin_of_text|>
    -0.08
    (\'
    -0.07
     Butt
    -0.07
     langu
    -0.07
    ï¿
    -0.07
    exampleInput
    -0.07
     ausp
    -0.07
    POSITIVE LOGITS
     Specifically
    0.10
    çī¹åĪ«
    0.09
     specifically
    0.09
    å°¤
    0.09
    主è¦ģ
    0.09
     actually
    0.08
     BUT
    0.08
     particularly
    0.08
    ä¸įäºĨ
    0.08
    aira
    0.08
    Activations Density 3.138%

    No Known Activations