© 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. 63626
    Prev
    Next
    INDEX
    Explanations

    will predicts action

    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
    aris
    -0.09
    achi
    -0.09
    çĶļèĩ³
    -0.09
    ivo
    -0.09
    ad
    -0.09
    akat
    -0.09
    assa
    -0.09
    ï½Ŀ
    -0.09
    uce
    -0.08
     radix
    -0.08
    POSITIVE LOGITS
     be
    0.22
    l
    0.20
    iams
    0.17
    fully
    0.15
    /is
    0.15
     not
    0.15
    /c
    0.15
     likely
    0.14
     moci
    0.14
     mÃŃt
    0.14
    Activations Density 0.102%

    No Known Activations