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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 53888
    Prev
    Next
    INDEX
    Explanations

    Acting/Responding in character

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .EntityFramework
    -0.07
     ui
    -0.07
    }↵↵↵
    -0.07
     arrives
    -0.06
     undercover
    -0.06
    persona
    -0.06
     si
    -0.06
     Yale
    -0.06
    _stuff
    -0.06
     же
    -0.06
    POSITIVE LOGITS
     Atlas
    0.07
    信息
    0.06
    _fname
    0.06
     перес
    0.06
    ulg
    0.06
     потрап
    0.06
     bakış
    0.06
    _RESOURCES
    0.06
    _DF
    0.06
    .Asset
    0.06
    Activations Density 0.041%

    No Known Activations