© 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. 109434
    Prev
    Next
    INDEX
    Explanations

    Ethical research with human subjects

    np_max-act · gemini-2.0-flash

    terms related to ethical and regulatory considerations in research, particularly involving human subjects.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects references to ethical and regulatory considerations in human-subjects research, such as protection of participants, informed consent, and oversight by ethics committees.

    oai_token-act-pair · o4-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
     denn
    -0.07
     ener
    -0.07
     swinger
    -0.06
    _MAY
    -0.06
    _prom
    -0.06
     workouts
    -0.06
     UITableViewDelegate
    -0.06
     Pills
    -0.06
    964
    -0.06
     Veg
    -0.06
    POSITIVE LOGITS
    Court
    0.07
    {↵
    0.06
    ạp
    0.06
    âte
    0.06
     Aluminum
    0.06
    她们
    0.06
    uly
    0.06
     дви
    0.06
     şeklinde
    0.06
    .place
    0.06
    Activations Density 0.015%

    No Known Activations