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. 15-RESID-POST-AA
    6. 79473
    Prev
    Next
    INDEX
    Explanations

    technical/engineering descriptions

    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
    کنان
    -0.06
     multic
    -0.06
     Diy
    -0.06
     Ripple
    -0.06
    Mock
    -0.06
    processor
    -0.06
     ***!↵
    -0.06
    .gs
    -0.06
    	pt
    -0.06
     tabela
    -0.06
    POSITIVE LOGITS
    HOW
    0.07
     lands
    0.07
     الرو
    0.07
     Rocks
    0.06
     현대
    0.06
    اخته
    0.06
     reliance
    0.06
     VII
    0.06
     bout
    0.06
    =>'
    0.06
    Activations Density 0.211%

    No Known Activations