© 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. 25070
    Prev
    Next
    INDEX
    Explanations

    eurhythmics, vulnerabilities, neurips

    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
    ãģ¨ãģį
    -0.16
    ãģ¨ãģĵãĤį
    -0.14
    ed
    -0.13
    ene
    -0.13
    en
    -0.12
    es
    -0.12
    ese
    -0.12
    ãģ¨æĢĿ
    -0.12
    ATION
    -0.11
    ens
    -0.11
    POSITIVE LOGITS
    hythm
    0.13
    ricane
    0.13
    ishment
    0.12
    thers
    0.12
    gh
    0.11
    ered
    0.11
    anga
    0.11
    ds
    0.11
    ales
    0.11
    er
    0.11
    Activations Density 0.079%

    No Known Activations