© 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. 46976
    Prev
    Next
    INDEX
    Explanations

    Amnesia: The Dark Descent

    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
     MAV
    -0.10
     Bij
    -0.09
     Ruf
    -0.09
    ijd
    -0.09
    za
    -0.09
    _MAY
    -0.08
     Howell
    -0.08
    oj
    -0.08
    .snap
    -0.08
    èĢ
    -0.08
    POSITIVE LOGITS
     Am
    0.26
     Commod
    0.19
    Am
    0.18
    .library
    0.17
    -Am
    0.15
     Morph
    0.15
     commod
    0.13
     morph
    0.13
    680
    0.13
     Paula
    0.12
    Activations Density 0.011%

    No Known Activations