Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88679
    Prev
    Next
    INDEX
    Explanations

    Polycystic Ovary Syndrome

    np_max-act · gemini-2.0-flash

    information related to diagnoses and criteria for Polycystic Ovary Syndrome (PCOS).

    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
     nelle
    -0.07
     трьох
    -0.07
     반
    -0.07
     trunk
    -0.06
     Instance
    -0.06
    isors
    -0.06
    _first
    -0.06
    aniu
    -0.06
     πρώτη
    -0.06
    ności
    -0.06
    POSITIVE LOGITS
    .getElementsBy
    0.08
    ("${
    0.06
    .getString
    0.06
     يمكن
    0.06
     SST
    0.06
     '''
    0.06
     rejoice
    0.06
     dominating
    0.06
    .paths
    0.06
     ammon
    0.06
    Activations Density 0.000%

    No Known Activations