© 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. 62038
    Prev
    Next
    INDEX
    Explanations

    lingüo-sintaxis, stylométrie, filosofÃŃa

    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
    олоÑĪ
    -0.12
    olojik
    -0.12
     theological
    -0.11
    ologically
    -0.11
    ográf
    -0.10
     physiological
    -0.10
     Psychological
    -0.10
    ologické
    -0.10
    ологиÑĩеÑģ
    -0.10
    apg
    -0.10
    POSITIVE LOGITS
    ศาสà¸ķร
    0.19
    istics
    0.19
    atics
    0.18
    ิศาสà¸ķร
    0.18
    ics
    0.17
    ÑģÑĤика
    0.17
    ology
    0.17
    ологиÑı
    0.16
    atology
    0.16
    etics
    0.16
    Activations Density 0.180%

    No Known Activations