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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 22504
    Prev
    Next
    INDEX
    Explanations

    Def

    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
    elez
    -0.06
    δος
    -0.06
     pork
    -0.06
     objet
    -0.06
     Chandler
    -0.06
     maliyet
    -0.06
    _house
    -0.06
    urances
    -0.06
     purposely
    -0.06
     Klopp
    -0.06
    POSITIVE LOGITS
     برابر
    0.07
    -II
    0.07
    准备
    0.07
    �
    0.07
    ському
    0.06
    廊
    0.06
     promoter
    0.06
    Shortly
    0.06
    (Double
    0.06
    NSInteger
    0.06
    Activations Density 0.005%

    No Known Activations