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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 93445
    Prev
    Next
    INDEX
    Explanations

    research methodology

    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
     hang
    -0.07
     shelf
    -0.06
     ideals
    -0.06
     issued
    -0.06
     болезни
    -0.06
     glory
    -0.06
     alerted
    -0.06
     misconception
    -0.06
    level
    -0.06
     slav
    -0.06
    POSITIVE LOGITS
    ucken
    0.07
    ?action
    0.07
     Featured
    0.07
     Len
    0.07
    OptionPane
    0.07
     बय
    0.07
    .sql
    0.06
    _Main
    0.06
    uren
    0.06
    numberOf
    0.06
    Activations Density 0.018%

    No Known Activations