© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33611
    Prev
    Next
    INDEX
    Explanations

    object will move

    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
    AccessType
    -0.10
     Transition
    -0.09
     Shr
    -0.09
     slack
    -0.08
    ument
    -0.08
     Morales
    -0.08
    MouseButton
    -0.08
    Meter
    -0.08
    -insert
    -0.08
     carg
    -0.08
    POSITIVE LOGITS
     move
    0.54
     movement
    0.54
     moved
    0.44
    移åĬ¨
    0.44
     moves
    0.43
     Move
    0.43
     Movement
    0.40
    移åĭķ
    0.40
    move
    0.40
    movement
    0.39
    Activations Density 0.119%

    No Known Activations