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. 23-RESID-POST-AA
    6. 104065
    Prev
    Next
    INDEX
    Explanations

    other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conversion
    -0.06
    表情
    -0.06
    '$
    -0.06
    Structured
    -0.06
     pork
    -0.06
    Power
    -0.06
    touches
    -0.06
     coaster
    -0.06
    <Address
    -0.06
     fuel
    -0.06
    POSITIVE LOGITS
     робіт
    0.07
    دانلود
    0.06
    βο
    0.06
     Turkish
    0.06
    )section
    0.06
    การท
    0.06
     TTC
    0.06
    deer
    0.06
    ุงเทพมหานคร
    0.06
    calendar
    0.06
    Activations Density 0.265%

    No Known Activations