© 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. 62857
    Prev
    Next
    INDEX
    Explanations

    potential problems and risks

    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
     humili
    -0.11
    /Peak
    -0.10
     disruptions
    -0.10
     didSelectRowAtIndexPath
    -0.09
     setbacks
    -0.09
     bá»ĭ
    -0.09
     FileAccess
    -0.09
     distur
    -0.09
     pes
    -0.09
     frustrations
    -0.09
    POSITIVE LOGITS
     problems
    0.25
     harm
    0.20
     Problems
    0.18
     problem
    0.18
     damage
    0.17
    problems
    0.16
     Proble
    0.16
     proble
    0.16
     probl
    0.16
    éĹ®é¢ĺ
    0.15
    Activations Density 0.101%

    No Known Activations