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. 73115
    Prev
    Next
    INDEX
    Explanations

    time

    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
    _manual
    -0.07
    height
    -0.07
    productos
    -0.07
     calibrated
    -0.07
     counting
    -0.07
     žád
    -0.07
    fast
    -0.06
     Natal
    -0.06
    .descripcion
    -0.06
    burn
    -0.06
    POSITIVE LOGITS
    .ForeColor
    0.06
    .buy
    0.06
     Ferm
    0.06
    ayscale
    0.06
     profund
    0.06
    ماری
    0.06
    (country
    0.06
     hemos
    0.06
     DataAccess
    0.06
    ��
    0.06
    Activations Density 0.016%

    No Known Activations