© 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. 32431
    Prev
    Next
    INDEX
    Explanations

    distinguishing concepts using rather than

    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
    _GF
    -0.10
    agas
    -0.10
    itr
    -0.09
    ral
    -0.09
    -less
    -0.08
    .BLL
    -0.08
     vừa
    -0.08
    VML
    -0.08
     haz
    -0.08
     eff
    -0.08
    POSITIVE LOGITS
     rather
    0.52
     chứ
    0.51
    rather
    0.39
     Rather
    0.32
     deÄŁil
    0.31
    Rather
    0.29
     instead
    0.26
    ãģ§ãģ¯ãģªãģı
    0.25
     ÙĪÙĦÙĬ
    0.25
    ï¼ĮèĢĮ
    0.23
    Activations Density 0.195%

    No Known Activations