© 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. 11-RESID-POST-AA
    6. 80459
    Prev
    Next
    INDEX
    Explanations

    controversy and debate

    np_max-act · gemini-2.0-flash

    instances of controversial or inappropriate humor.

    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
    unga
    -0.07
     fathers
    -0.07
     flash
    -0.07
     Slow
    -0.07
     kissing
    -0.06
    Sr
    -0.06
    rea
    -0.06
    Noise
    -0.06
    ike
    -0.06
    changer
    -0.06
    POSITIVE LOGITS
    rparr
    0.07
    (&_
    0.06
    ']]['
    0.06
    LETE
    0.06
     dém
    0.06
    director
    0.06
    ¯¯¯¯
    0.06
    <=$
    0.06
    جمة
    0.05
     Whale
    0.05
    Activations Density 0.103%

    No Known Activations