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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    11. 87640
    Prev
    Next
    INDEX
    Explanations

    genetic

    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
     Sensor
    -0.07
     frontend
    -0.07
    修改
    -0.07
     keyword
    -0.06
     floor
    -0.06
    .gdx
    -0.06
     cluster
    -0.06
    ät
    -0.06
     elf
    -0.06
    #w
    -0.06
    POSITIVE LOGITS
     convertible
    0.07
    静
    0.07
     Độ
    0.06
    	Py
    0.06
    ('.')[
    0.06
    .rank
    0.06
     نخ
    0.06
     AUG
    0.06
    ;",↵
    0.06
     trial
    0.06
    Activations Density 0.017%

    No Known Activations