© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44524
    Prev
    Next
    INDEX
    Explanations

    graphic violence and sexuality

    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
    edException
    -0.09
    Viet
    -0.09
     convers
    -0.09
    RelativeTo
    -0.09
    ocide
    -0.09
    591
    -0.09
    wizard
    -0.08
    ers
    -0.08
     cum
    -0.08
    631
    -0.08
    POSITIVE LOGITS
    ous
    0.12
    ence
    0.11
     femmes
    0.11
    ented
    0.10
    alia
    0.10
    encia
    0.10
     physical
    0.10
     streak
    0.09
     Vor
    0.09
    uous
    0.09
    Activations Density 0.024%

    No Known Activations