© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 18580
    Prev
    Next
    INDEX
    Explanations

    No entanto, se, ich, как

    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
    Negative Logits
    xmm
    -0.08
    ÏĦÏģο
    -0.08
    iry
    -0.08
    nob
    -0.08
    ombre
    -0.08
    LEM
    -0.08
     Seit
    -0.08
     à¹ģล
    -0.07
    esel
    -0.07
     Mature
    -0.07
    POSITIVE LOGITS
    æĪijçļĦ
    0.28
     my
    0.28
     myself
    0.25
     tôi
    0.21
     mijn
    0.20
    æĪij
    0.19
     meu
    0.19
     мо
    0.19
     minha
    0.19
    my
    0.18
    Activations Density 0.162%

    No Known Activations