© 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. 48899
    Prev
    Next
    INDEX
    Explanations

    Third, 3rd, Tercer

    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
     Second
    -0.18
    äºĮ
    -0.16
     Secondly
    -0.16
    ãĢģäºĮ
    -0.15
     äºĮ
    -0.14
    .Second
    -0.13
    Second
    -0.13
     SECOND
    -0.13
    ?,?,?,?,
    -0.13
    SECOND
    -0.12
    POSITIVE LOGITS
     third
    0.74
    third
    0.59
    第ä¸ī
    0.58
     Third
    0.56
    Third
    0.54
     THIRD
    0.53
     第ä¸ī
    0.52
     üçüncü
    0.52
     ÑĤÑĢеÑĤÑĮ
    0.51
     tercer
    0.49
    Activations Density 0.301%

    No Known Activations