© 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. 52767
    Prev
    Next
    INDEX
    Explanations

    Code/chat snippets

    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
     Snow
    -0.07
    Sale
    -0.07
     conduc
    -0.06
    [][]
    -0.06
     Vest
    -0.06
    IVING
    -0.06
    єн
    -0.06
    _BAD
    -0.06
    _lines
    -0.06
    ADI
    -0.06
    POSITIVE LOGITS
     Τι
    0.08
     روسی
    0.06
    一种
    0.06
    FormField
    0.06
    .setHorizontal
    0.06
     ".",
    0.06
    (ct
    0.06
    ایل
    0.06
    (Util
    0.06
     urge
    0.06
    Activations Density 0.046%

    No Known Activations