© 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
    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. 36712
    Prev
    Next
    INDEX
    Explanations

    The number one

    np_max-act · gemini-2.0-flash
    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
    تی
    -0.07
     Wilderness
    -0.06
     Life
    -0.06
    动生成
    -0.06
    асс
    -0.06
    athom
    -0.06
    onald
    -0.06
    (value
    -0.06
     Bazı
    -0.05
     Whites
    -0.05
    POSITIVE LOGITS
     plur
    0.06
     kys
    0.06
     ASA
    0.06
     slur
    0.06
    Inv
    0.06
    	glut
    0.06
    엔
    0.06
    ToDevice
    0.06
     iP
    0.06
    이라
    0.06
    Activations Density 0.003%

    No Known Activations