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. 15-RESID-POST-AA
    6. 684
    Prev
    Next
    INDEX
    Explanations

    code and special characters

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cover
    -0.06
    法
    -0.06
    ysql
    -0.06
    ีด
    -0.06
    catid
    -0.06
    gender
    -0.06
     BEN
    -0.06
    money
    -0.06
     Stir
    -0.06
    Feel
    -0.06
    POSITIVE LOGITS
    _interrupt
    0.07
    .codes
    0.07
        ↵    ↵    ↵    ↵
    0.06
     MODIFY
    0.06
    	cm
    0.06
    -mode
    0.06
    	↵	↵↵
    0.06
     membranes
    0.06
     *)↵
    0.06
     такий
    0.06
    Activations Density 0.005%

    No Known Activations