Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 19-RESID-POST-AA
    6. 127281
    Prev
    Next
    INDEX
    Explanations

    historical events

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .RowCount
    -0.07
    .Video
    -0.07
     mantra
    -0.07
    stories
    -0.07
    ських
    -0.06
    ктів
    -0.06
    Injection
    -0.06
    シ
    -0.06
     Leap
    -0.06
    lots
    -0.06
    POSITIVE LOGITS
     drip
    0.06
     blown
    0.06
     thinly
    0.06
    ony
    0.06
    蛋
    0.06
    ए
    0.06
    -night
    0.06
    (description
    0.05
    ¯Â
    0.05
     spor
    0.05
    Activations Density 0.059%

    No Known Activations