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. 73102
    Prev
    Next
    INDEX
    Explanations

    .rb

    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
     Completion
    -0.07
     Count
    -0.07
    .EndsWith
    -0.06
    	getline
    -0.06
     Inter
    -0.06
     refugee
    -0.06
     retrieve
    -0.06
     Attacks
    -0.06
    ');?></
    -0.06
     combines
    -0.06
    POSITIVE LOGITS
     맡
    0.07
    、一
    0.06
    中心
    0.06
    uong
    0.06
    лугов
    0.06
    splash
    0.06
     adaptor
    0.06
     xong
    0.06
    xo
    0.06
     nickname
    0.06
    Activations Density 0.013%

    No Known Activations