Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 80579
    Prev
    Next
    INDEX
    Explanations

    /compiler

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vượt
    -0.06
     Kash
    -0.06
    (fun
    -0.06
     ріш
    -0.06
    ิกายน
    -0.06
    ;
    
    
    ↵
    -0.06
    _topics
    -0.06
     portraits
    -0.06
    νοια
    -0.05
     joking
    -0.05
    POSITIVE LOGITS
     artist
    0.07
     setColor
    0.07
    elling
    0.07
    Orm
    0.07
    iştir
    0.06
    	state
    0.06
     ''){↵
    0.06
    ()]);↵
    0.06
     discard
    0.06
     divers
    0.06
    Activations Density 0.001%

    No Known Activations