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. 11-RESID-POST-AA
    6. 21635
    Prev
    Next
    INDEX
    Explanations

    Internet activity

    np_max-act · gemini-2.0-flash

    references to the internet and digital communication, such as online platforms, social media, websites, and web activity

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     tourism
    -0.07
     soaked
    -0.07
    cession
    -0.07
     heterosexual
    -0.07
     Kids
    -0.07
     chức
    -0.06
     Taxi
    -0.06
     Premier
    -0.06
     Trump
    -0.06
     Literature
    -0.06
    POSITIVE LOGITS
     หร
    0.06
     pů
    0.06
     eql
    0.06
    EDIA
    0.06
    Ğ
    0.06
    alph
    0.06
    .readFileSync
    0.06
    ظˆط
    0.06
    rens
    0.06
     εμφ
    0.06
    Activations Density 0.167%

    No Known Activations