© 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. 59173
    Prev
    Next
    INDEX
    Explanations

    to achieve, to choose, to generate

    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
    iga
    -0.09
    lico
    -0.08
    uck
    -0.08
     pisc
    -0.08
    iasi
    -0.08
     aggravated
    -0.08
     Copp
    -0.08
    entic
    -0.08
     Glover
    -0.08
    à¹Ĥย
    -0.08
    POSITIVE LOGITS
     increased
    0.13
     measures
    0.13
    Maint
    0.13
     mant
    0.12
     maintain
    0.12
    æıIJé«ĺ
    0.12
     maintaining
    0.12
     Maint
    0.11
     Mant
    0.11
     measure
    0.11
    Activations Density 0.308%

    No Known Activations