© 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. 8868
    Prev
    Next
    INDEX
    Explanations

    diffuse through, certainty through

    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
    fak
    -0.09
     Zub
    -0.09
    illez
    -0.09
    aker
    -0.08
    âī¦
    -0.08
     Parad
    -0.08
    tae
    -0.08
     Templ
    -0.08
     Butt
    -0.08
    kek
    -0.07
    POSITIVE LOGITS
     such
    0.11
     ÙħØ«ÙĦا
    0.10
     might
    0.10
    IFA
    0.10
     say
    0.09
     perhaps
    0.09
    imb
    0.09
    856
    0.09
     employed
    0.08
    such
    0.08
    Activations Density 0.129%

    No Known Activations