© 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. 11-RESID-POST-AA
    11. 75119
    Prev
    Next
    INDEX
    Explanations

    controversial topics

    np_max-act · gemini-2.0-flash

    content that pushes the boundaries of ethical and legal standards.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     penis
    -0.07
     technique
    -0.07
     エ
    -0.07
    914
    -0.06
    capacity
    -0.06
    )");↵↵
    -0.06
    ovie
    -0.06
    Your
    -0.06
    管理员
    -0.06
    limited
    -0.06
    POSITIVE LOGITS
     block
    0.07
     dipping
    0.06
     порт
    0.06
     aug
    0.06
    -share
    0.06
     coolant
    0.06
     etree
    0.06
     Essence
    0.06
     honesty
    0.06
     blockDim
    0.06
    Activations Density 0.018%

    No Known Activations