Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 18287
    Prev
    Next
    INDEX
    Explanations

    spectro

    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
     TIM
    -0.07
    TOKEN
    -0.07
    地址
    -0.07
    .println
    -0.06
     CPI
    -0.06
    .export
    -0.06
     damping
    -0.06
     goat
    -0.06
     workshop
    -0.06
    VIOUS
    -0.06
    POSITIVE LOGITS
    $temp
    0.06
    Attachments
    0.06
     Norwich
    0.06
    AMS
    0.06
     χρήση
    0.06
     withRouter
    0.06
    �
    0.06
     Thurs
    0.06
     depressed
    0.06
    			
    ↵
    0.06
    Activations Density 0.010%

    No Known Activations