© 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. 64019
    Prev
    Next
    INDEX
    Explanations

    authorized and unauthorized access

    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
    659
    -0.09
    uate
    -0.09
    orr
    -0.09
    AuthToken
    -0.09
    ialis
    -0.09
    flash
    -0.09
    ouri
    -0.09
    pace
    -0.09
    apt
    -0.08
    icken
    -0.08
    POSITIVE LOGITS
     access
    0.20
    /lic
    0.14
     personnel
    0.14
     persons
    0.14
    AccessException
    0.13
    access
    0.12
    -access
    0.12
    zed
    0.12
    Access
    0.11
     personel
    0.11
    Activations Density 0.012%

    No Known Activations