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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 107856
    Prev
    Next
    INDEX
    Explanations

    online medical advice

    np_max-act · gemini-2.0-flash

    first-person assistant disclaimers that refuse or limit providing medical advice or diagnoses (e.g., "I don't/can't provide medical advice" statements).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hma
    -0.07
    ापक
    -0.07
    Objects
    -0.07
    損
    -0.06
     Ladies
    -0.06
     sweaty
    -0.06
     coma
    -0.06
     FUCK
    -0.06
    ENS
    -0.06
     такой
    -0.06
    POSITIVE LOGITS
    .flowLayoutPanel
    0.07
     designate
    0.06
    EdgeInsets
    0.06
    ýval
    0.06
    Xi
    0.06
    _FieldOffsetTable
    0.06
    BUTTONDOWN
    0.06
    ственным
    0.06
    rieve
    0.06
    .hand
    0.06
    Activations Density 0.147%

    No Known Activations