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. 23-RESID-POST-AA
    6. 103959
    Prev
    Next
    INDEX
    Explanations

    best practices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     кол
    -0.07
     doubles
    -0.07
     sto
    -0.06
     să
    -0.06
     用户
    -0.06
     वक
    -0.06
     Кол
    -0.06
    CTest
    -0.06
    	title
    -0.06
     avez
    -0.06
    POSITIVE LOGITS
     Sasha
    0.07
     Cleaning
    0.06
    _th
    0.06
     omas
    0.06
     باشگاه
    0.06
     bör
    0.06
     Braves
    0.06
     rejection
    0.06
    оград
    0.06
     Quarry
    0.06
    Activations Density 0.160%

    No Known Activations