© 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. 56512
    Prev
    Next
    INDEX
    Explanations

    your needs or goals

    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
    785
    -0.09
     شع
    -0.09
    atest
    -0.08
    ouser
    -0.08
     whereabouts
    -0.08
    768
    -0.08
    longleftrightarrow
    -0.08
    abaj
    -0.08
    ât
    -0.08
     directions
    -0.08
    POSITIVE LOGITS
     purposes
    0.35
     needs
    0.34
     situation
    0.31
    needs
    0.28
     Needs
    0.27
     particular
    0.25
    Needs
    0.25
    æĥħåĨµ
    0.20
     Situation
    0.20
     situations
    0.19
    Activations Density 0.047%

    No Known Activations