© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 105401
    Prev
    Next
    INDEX
    Explanations

    hung

    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
    Geom
    -0.06
    wor
    -0.06
    MBED
    -0.06
     вну
    -0.06
    lossen
    -0.06
     ciz
    -0.06
    _employee
    -0.06
    гляд
    -0.06
     aes
    -0.06
     scop
    -0.06
    POSITIVE LOGITS
    شركة
    0.07
     Quận
    0.06
    _TEST
    0.06
    submit
    0.06
    ,min
    0.06
    ialias
    0.06
    ")
↵
↵
    0.06
    	addr
    0.06
     extension
    0.06
    *B
    0.06
    Activations Density 0.022%

    No Known Activations