© 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. 92020
    Prev
    Next
    INDEX
    Explanations

    internet

    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
     하고
    -0.07
     укра
    -0.07
    	esc
    -0.06
    omp
    -0.06
    anye
    -0.06
    uren
    -0.06
    _:*
    -0.06
     attends
    -0.06
    这
    -0.06
     sorumlu
    -0.06
    POSITIVE LOGITS
     Internet
    0.07
     vign
    0.06
    _e
    0.06
    definition
    0.06
     QT
    0.06
     upbeat
    0.06
    _RUNNING
    0.06
    été
    0.06
     nhuận
    0.06
    egade
    0.06
    Activations Density 0.019%

    No Known Activations