© 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. 63637
    Prev
    Next
    INDEX
    Explanations

    classifications or ranges

    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
    andbox
    -0.12
    ule
    -0.11
    agar
    -0.10
     Anders
    -0.10
    apos
    -0.09
    agus
    -0.09
    uler
    -0.09
    antor
    -0.09
    ama
    -0.09
    -vers
    -0.09
    POSITIVE LOGITS
     passing
    0.16
    ãģ«ãģĭ
    0.13
    ãģ¾ãģ§
    0.12
    ãģĿãģĹãģ¦
    0.12
     via
    0.12
     گرÙģتÙĩ
    0.12
    åĪ°
    0.12
    ê¹Įì§Ģ
    0.11
     Passing
    0.11
    ä¹ĥ
    0.11
    Activations Density 0.061%

    No Known Activations