© 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. 58534
    Prev
    Next
    INDEX
    Explanations

    point of view from

    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
     storyline
    -0.13
     narratives
    -0.10
     Khan
    -0.09
    408
    -0.09
     titul
    -0.08
    ibo
    -0.08
    aty
    -0.08
    reh
    -0.08
    igit
    -0.08
    peater
    -0.08
    POSITIVE LOGITS
     scene
    0.18
     dialogue
    0.16
     fo
    0.14
     Scene
    0.14
     scenes
    0.14
     reader
    0.14
     Dialogue
    0.13
     GMC
    0.13
     readers
    0.13
    Dialogue
    0.12
    Activations Density 0.189%

    No Known Activations