© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 4646
    Prev
    Next
    INDEX
    Explanations

    Risk

    np_max-act · gemini-2.0-flash

    insurance and risk management contexts, especially legal or claims discussions involving coverage, insurers, and duties like defend/indemnify.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misdemeanor
    -0.06
    ("**
    -0.06
     jade
    -0.06
     şimdi
    -0.06
     kz
    -0.06
    tokenId
    -0.06
    -power
    -0.06
    ella
    -0.06
    ุม
    -0.06
     onTap
    -0.06
    POSITIVE LOGITS
    ]).↵
    0.07
     tố
    0.07
    -Tr
    0.07
    horse
    0.06
     національ
    0.06
     investigate
    0.06
     للم
    0.06
    RED
    0.06
     Go
    0.06
    uded
    0.06
    Activations Density 0.174%

    No Known Activations