© 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. 23462
    Prev
    Next
    INDEX
    Explanations

    harm to individuals or others

    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
    atican
    -0.09
    QN
    -0.09
    umi
    -0.09
     prejudice
    -0.08
    íıŃ
    -0.08
    nown
    -0.08
     Rit
    -0.08
    ĥģ
    -0.08
     sexually
    -0.08
     rescue
    -0.08
    POSITIVE LOGITS
     individuals
    0.19
     both
    0.18
     Individuals
    0.15
     individual
    0.14
    both
    0.14
     involved
    0.14
    individual
    0.14
     relationships
    0.13
     parties
    0.13
     individ
    0.12
    Activations Density 0.054%

    No Known Activations