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. 26058
    Prev
    Next
    INDEX
    Explanations

    Changes over time

    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
     novels
    -0.07
    不是
    -0.07
    _name
    -0.07
     Southern
    -0.07
     gap
    -0.07
    -goal
    -0.07
     maxHeight
    -0.07
     tiger
    -0.07
     rio
    -0.07
     beetle
    -0.07
    POSITIVE LOGITS
    іла
    0.06
    ycz
    0.06
    684
    0.06
    :{}
    0.06
    ينا
    0.06
     Hindered
    0.06
    축
    0.05
    تامبر
    0.05
    		    ↵
    0.05
     在线
    0.05
    Activations Density 0.042%

    No Known Activations