© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 30971
    Prev
    Next
    INDEX
    Explanations

    ebike trail distance

    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
     hiking
    -0.20
     walking
    -0.17
     walkers
    -0.17
     Walking
    -0.17
    Walking
    -0.16
    walking
    -0.15
     hikes
    -0.15
     walked
    -0.14
     walker
    -0.13
     walks
    -0.13
    POSITIVE LOGITS
     ped
    0.20
     gravel
    0.17
     ride
    0.16
     Ped
    0.15
    Ped
    0.15
     fondo
    0.14
     saddle
    0.14
     Tour
    0.14
     Schw
    0.14
     jerseys
    0.13
    Activations Density 0.019%

    No Known Activations