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. 11-RESID-POST-AA
    6. 36475
    Prev
    Next
    INDEX
    Explanations

    the, is

    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
    部屋
    -0.07
    _partition
    -0.06
     page
    -0.06
    antar
    -0.06
    *@
    -0.06
    dash
    -0.06
     ethnic
    -0.06
     bmi
    -0.06
    acular
    -0.06
    (INT
    -0.06
    POSITIVE LOGITS
    	iVar
    0.06
     Гор
    0.06
    .removeClass
    0.06
    ยนต
    0.06
    _nullable
    0.06
    .getElementsByClassName
    0.06
     d
    0.06
     dedic
    0.06
     πέ
    0.06
     lebih
    0.06
    Activations Density 0.007%

    No Known Activations