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. 51260
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Geile
    -0.07
    .Designer
    -0.07
     Middleware
    -0.07
     Character
    -0.07
     Discussion
    -0.06
     Disclaimer
    -0.06
     harmonic
    -0.06
     Stage
    -0.06
    cccc
    -0.06
    creation
    -0.06
    POSITIVE LOGITS
    	sound
    0.07
     올
    0.07
    震
    0.07
     cv
    0.07
     控
    0.06
    marvin
    0.06
    土
    0.06
    '];
    ↵
    0.06
    іл
    0.06
     cord
    0.06
    Activations Density 0.066%

    No Known Activations