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. 24566
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash

    quoted text, particularly quotes in non-English languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @andyrdt
    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
     �
    -0.07
     autre
    -0.07
    ımızda
    -0.06
    辛
    -0.06
     apis
    -0.06
     آش
    -0.06
     привы
    -0.06
    
    -0.06
     воно
    -0.06
     SPEED
    -0.06
    POSITIVE LOGITS
    ivid
    0.07
     professional
    0.07
    очной
    0.06
     Noel
    0.06
    lehem
    0.06
    brightness
    0.06
     impose
    0.06
     Integr
    0.06
    (group
    0.06
     Gray
    0.06
    Activations Density 0.210%

    No Known Activations