© 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. 28930
    Prev
    Next
    INDEX
    Explanations

    harm, interference, decline

    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
     worsening
    -0.11
     wors
    -0.11
    REA
    -0.10
    ırı
    -0.10
     adversely
    -0.10
     CAUSED
    -0.09
    WebResponse
    -0.09
     overwhel
    -0.09
     rebut
    -0.09
    LastError
    -0.09
    POSITIVE LOGITS
     er
    0.29
     threat
    0.28
     erosion
    0.26
     challenge
    0.25
     dent
    0.24
     enc
    0.23
     threats
    0.22
     attack
    0.22
     chip
    0.22
     Threat
    0.22
    Activations Density 0.118%

    No Known Activations