© 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. 41176
    Prev
    Next
    INDEX
    Explanations

    avoidance of negative consequences

    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
    ÏģιÏĥ
    -0.10
     rather
    -0.09
    缸å½ĵ
    -0.09
     Benny
    -0.09
    pit
    -0.09
     pretty
    -0.09
    ekil
    -0.09
     inaccur
    -0.08
    alach
    -0.08
     Mein
    -0.08
    POSITIVE LOGITS
     nor
    0.30
     anymore
    0.23
     too
    0.22
    太
    0.20
    nor
    0.19
     TOO
    0.19
    too
    0.18
     ÑģлиÑĪком
    0.17
     太
    0.17
     Nor
    0.17
    Activations Density 0.123%

    No Known Activations