© 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. 49525
    Prev
    Next
    INDEX
    Explanations

    get away with

    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
    Current
    -0.10
    Data
    -0.10
    Value
    -0.09
    ëį°ìĿ´íĬ¸
    -0.09
    Client
    -0.09
    ENAME
    -0.08
    LOB
    -0.08
    keit
    -0.08
    AndGet
    -0.08
     mag
    -0.08
    POSITIVE LOGITS
     rid
    0.22
     away
    0.13
    chas
    0.12
     carried
    0.12
     ahead
    0.12
    .chomp
    0.11
    ahead
    0.11
     mileage
    0.11
    cha
    0.11
     Rid
    0.11
    Activations Density 0.022%

    No Known Activations