© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 95677
    Prev
    Next
    INDEX
    Explanations

    adrenal adenoma

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цу
    -0.07
     desert
    -0.07
     estud
    -0.06
     gave
    -0.06
     gives
    -0.06
    .off
    -0.06
    "<
    -0.06
    [][
    -0.06
    ,err
    -0.06
     shipping
    -0.06
    POSITIVE LOGITS
    千
    0.06
    석
    0.06
    -Requested
    0.06
    tables
    0.06
    (eventName
    0.06
     双
    0.06
     ủy
    0.06
    .capture
    0.06
     BTC
    0.06
     vyb
    0.06
    Activations Density 0.034%

    No Known Activations