© 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. 65952
    Prev
    Next
    INDEX
    Explanations

    assault/violence encounters

    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
    ेच
    -0.06
    pants
    -0.06
    "$
    -0.06
    groupId
    -0.06
     див
    -0.06
     chtěl
    -0.05
     ""){↵
    -0.05
     sizin
    -0.05
    882
    -0.05
     rav
    -0.05
    POSITIVE LOGITS
    _categories
    0.08
     ordinance
    0.07
     М
    0.07
    .getProperty
    0.07
    online
    0.07
     dame
    0.07
     날짜
    0.07
     colorWith
    0.07
     Luxembourg
    0.06
    onse
    0.06
    Activations Density 0.048%

    No Known Activations