© 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
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 7898
    Prev
    Next
    INDEX
    Explanations

    verb "to be"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    please
    -0.07
    niční
    -0.06
    ัฒนา
    -0.06
     Low
    -0.06
     agli
    -0.06
    gebung
    -0.06
     address
    -0.06
     captivity
    -0.06
    лугов
    -0.06
    .…↵↵
    -0.06
    POSITIVE LOGITS
     english
    0.07
     English
    0.07
     Soph
    0.07
    |max
    0.07
     Lud
    0.07
     synchronous
    0.06
     منط
    0.06
    	length
    0.06
     soph
    0.06
    ],[-
    0.06
    Activations Density 0.102%

    No Known Activations