© 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. 59430
    Prev
    Next
    INDEX
    Explanations

    consistent progress and standards

    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
     -*-č\n
    -0.11
    ledge
    -0.11
    ³ç´°
    -0.10
    704
    -0.10
    Fcn
    -0.09
    ê°Ŀ
    -0.09
    GraphNode
    -0.09
    _tD
    -0.09
    EMPLARY
    -0.08
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.08
    POSITIVE LOGITS
    ently
    0.21
    ency
    0.19
    cy
    0.17
    encies
    0.16
    antly
    0.16
    emente
    0.16
    ancy
    0.13
    aneously
    0.13
    aneous
    0.13
    ality
    0.12
    Activations Density 0.020%

    No Known Activations