© 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. 30370
    Prev
    Next
    INDEX
    Explanations

    State Street services

    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
    stamp
    -0.11
    -s
    -0.11
    stub
    -0.10
    stage
    -0.09
    -S
    -0.09
     ladder
    -0.09
    /state
    -0.09
     stagnant
    -0.09
    Âłs
    -0.09
    statuses
    -0.09
    POSITIVE LOGITS
     st
    0.31
     ST
    0.28
    .st
    0.27
    .St
    0.27
     St
    0.25
    (st
    0.25
    \tst
    0.23
    St
    0.23
    (ST
    0.22
     СÑĤ
    0.22
    Activations Density 0.121%

    No Known Activations