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

    Neuronpedia

    APICircuit 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. 80862
    Prev
    Next
    INDEX
    Explanations

    this

    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
     joker
    -0.07
    DidEnter
    -0.07
     queer
    -0.06
     aquatic
    -0.06
     appropriated
    -0.06
    人民共和国
    -0.06
     razor
    -0.06
     неї
    -0.06
    _inicio
    -0.06
     Shiite
    -0.06
    POSITIVE LOGITS
    (Value
    0.07
     dataType
    0.07
    ===============↵
    0.07
     tickets
    0.06
    (DWORD
    0.06
     wary
    0.06
     unacceptable
    0.06
    unsubscribe
    0.06
    :',↵
    0.06
    			 ↵
    0.06
    Activations Density 0.055%

    No Known Activations