© 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. 50959
    Prev
    Next
    INDEX
    Explanations

    the journey, stresses, need, more

    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
     fate
    -0.09
    elic
    -0.09
    072
    -0.09
    475
    -0.09
    ile
    -0.09
     ratt
    -0.09
    137
    -0.09
    ogen
    -0.09
    311
    -0.09
    est
    -0.09
    POSITIVE LOGITS
     things
    0.14
     Gott
    0.11
    anine
    0.10
     Dal
    0.10
     act
    0.10
    getApplication
    0.09
     foods
    0.09
     synonyms
    0.09
    things
    0.09
    xygen
    0.09
    Activations Density 0.118%

    No Known Activations