© 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. 20311
    Prev
    Next
    INDEX
    Explanations

    closed or locked door

    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
     UNS
    -0.10
    imbus
    -0.10
    ãĤŀ
    -0.10
    ahy
    -0.10
    onda
    -0.10
    alink
    -0.10
     Opening
    -0.10
     unf
    -0.09
    ertz
    -0.09
    (scroll
    -0.09
    POSITIVE LOGITS
     shut
    0.25
     lock
    0.24
     closed
    0.23
     locks
    0.21
     locked
    0.21
     Lock
    0.20
     locking
    0.20
     LOCK
    0.19
    éĶģ
    0.19
    .lock
    0.19
    Activations Density 0.045%

    No Known Activations