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. 11-RESID-POST-AA
    6. 21799
    Prev
    Next
    INDEX
    Explanations

    0

    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
     nepří
    -0.08
    딩
    -0.07
     rant
    -0.07
    nant
    -0.07
     Dispatcher
    -0.06
     Dort
    -0.06
    (chan
    -0.06
     бать
    -0.06
     cornerback
    -0.06
     HDR
    -0.06
    POSITIVE LOGITS
    0
    0.09
    10
    0.09
    50
    0.08
     Open
    0.08
     cooler
    0.07
     Golden
    0.07
     boycott
    0.07
     effective
    0.07
     K
    0.07
    WARE
    0.07
    Activations Density 0.028%

    No Known Activations