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. 34879
    Prev
    Next
    INDEX
    Explanations

    the

    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
    اع
    -0.07
     hưởng
    -0.06
    �
    -0.06
    OS
    -0.06
     نب
    -0.06
    	width
    -0.06
    background
    -0.06
    .Total
    -0.06
     fifth
    -0.06
    ////////////////////////////////////////////////////////////////////////////////
    -0.06
    POSITIVE LOGITS
     Augustine
    0.06
     боль
    0.06
    .SerializeObject
    0.06
    ologické
    0.06
     clues
    0.06
     ```↵
    0.06
     looph
    0.06
     immer
    0.06
    createdAt
    0.06
    のも
    0.06
    Activations Density 0.019%

    No Known Activations