© 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. 3051
    Prev
    Next
    INDEX
    Explanations

    refuel and keep, reflect, rest

    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
     resc
    -0.09
    ullo
    -0.09
    heimer
    -0.09
    reopen
    -0.09
     airl
    -0.08
    veau
    -0.08
     Tubes
    -0.08
     loung
    -0.08
    orman
    -0.08
    èĤ¯
    -0.08
    POSITIVE LOGITS
     reg
    0.24
     recover
    0.18
     rest
    0.16
     reflect
    0.15
     recovery
    0.14
     recovered
    0.14
     ref
    0.14
     decom
    0.14
     refresh
    0.13
    (ref
    0.13
    Activations Density 0.041%

    No Known Activations