© 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. 58508
    Prev
    Next
    INDEX
    Explanations

    forgetting all instructions

    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
    unds
    -0.10
    endale
    -0.10
    653
    -0.10
    illo
    -0.09
    794
    -0.09
    criptor
    -0.09
     Schwarz
    -0.09
    /of
    -0.09
    aval
    -0.09
    stadt
    -0.09
    POSITIVE LOGITS
    fulness
    0.20
    ful
    0.16
    table
    0.16
     forget
    0.16
     about
    0.16
    ting
    0.15
    tings
    0.15
     forgot
    0.14
    å¿ĺ
    0.13
    ten
    0.13
    Activations Density 0.017%

    No Known Activations