© 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. 14180
    Prev
    Next
    INDEX
    Explanations

    cannot express or comply

    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
     Kel
    -0.09
     Decision
    -0.09
    Serial
    -0.09
    ubes
    -0.09
    .lwjgl
    -0.08
     Angus
    -0.08
    ossier
    -0.08
    iere
    -0.08
    assa
    -0.08
    833
    -0.08
    POSITIVE LOGITS
     statements
    0.12
     statement
    0.12
     obliged
    0.11
     response
    0.11
     accommod
    0.10
    otoxic
    0.10
     cooper
    0.10
    enant
    0.10
     accommodate
    0.10
     answer
    0.09
    Activations Density 0.050%

    No Known Activations