© 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. 62716
    Prev
    Next
    INDEX
    Explanations

    flaking out on

    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
    ãĤ¦ãĥĪ
    -0.09
     thôi
    -0.09
    foon
    -0.09
    âī¦
    -0.09
     resignation
    -0.08
     ban
    -0.08
    ugal
    -0.08
     Böl
    -0.08
     Forge
    -0.08
    ç¦ģæŃ¢
    -0.08
    POSITIVE LOGITS
    çĪ½
    0.15
     bail
    0.14
     ren
    0.14
     flakes
    0.14
     ghost
    0.13
    flake
    0.13
     unreliable
    0.13
     Bail
    0.13
    ghost
    0.13
     promises
    0.12
    Activations Density 0.088%

    No Known Activations