© 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. 59909
    Prev
    Next
    INDEX
    Explanations

    language fragments

    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
     himself
    -0.23
     stesso
    -0.18
     electrónico
    -0.17
     italiano
    -0.15
     завиÑģим
    -0.15
     français
    -0.14
     koji
    -0.14
     público
    -0.13
     должен
    -0.12
     Himself
    -0.12
    POSITIVE LOGITS
     herself
    0.42
     italiana
    0.22
     коÑĤоÑĢаÑı
    0.20
     pública
    0.19
     à¤Ĺà¤Ī
    0.18
     бÑĭла
    0.18
     misma
    0.18
    ÑĪла
    0.17
    Ñİ
    0.17
     должна
    0.17
    Activations Density 0.364%

    No Known Activations