© 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. 61885
    Prev
    Next
    INDEX
    Explanations

    cache behavior or idempotency

    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
     Dil
    -0.10
     proprietary
    -0.10
     dil
    -0.10
    latent
    -0.09
    ossa
    -0.09
     feathers
    -0.09
    oreach
    -0.08
    ＼＼
    -0.08
     Campos
    -0.08
    legacy
    -0.08
    POSITIVE LOGITS
     cache
    0.20
     memo
    0.20
    cache
    0.19
    (cache
    0.18
    ç¼ĵ
    0.18
    memo
    0.18
     Memo
    0.18
    .cache
    0.18
     Cache
    0.17
    Memo
    0.17
    Activations Density 0.041%

    No Known Activations