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. 15-RESID-POST-AA
    6. 1089
    Prev
    Next
    INDEX
    Explanations

    with

    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
    (Job
    -0.07
     midd
    -0.07
     computation
    -0.07
    ASF
    -0.06
     Fang
    -0.06
    [tmp
    -0.06
    getProperty
    -0.06
     Гор
    -0.06
     factorial
    -0.06
    غيل
    -0.06
    POSITIVE LOGITS
    .Key
    0.07
    	false
    0.06
    ieder
    0.06
    leine
    0.06
    animate
    0.06
     Cooking
    0.06
    Anthony
    0.06
    ımız
    0.06
     gdy
    0.06
     ARTICLE
    0.06
    Activations Density 0.022%

    No Known Activations