© 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. 15-RESID-POST-AA
    6. 79403
    Prev
    Next
    INDEX
    Explanations

    AF

    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
    ryfall
    -0.06
    ới
    -0.06
    izace
    -0.06
    pecia
    -0.06
    +");↵
    -0.06
    Apart
    -0.06
    	GPIO
    -0.06
    illator
    -0.06
    stal
    -0.06
     Recap
    -0.06
    POSITIVE LOGITS
    .poly
    0.06
    >{@
    0.06
    编
    0.06
     Authorized
    0.06
    oupon
    0.06
    自
    0.06
     техничес
    0.06
     accustomed
    0.06
    monster
    0.06
     ترک
    0.06
    Activations Density 0.008%

    No Known Activations