© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 37843
    Prev
    Next
    INDEX
    Explanations

    child speech

    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
    	with
    -0.06
     Dre
    -0.06
     Operations
    -0.06
    IGHLIGHT
    -0.06
     Exchange
    -0.05
     flare
    -0.05
    Parts
    -0.05
     Well
    -0.05
     Occasionally
    -0.05
     Items
    -0.05
    POSITIVE LOGITS
    ntity
    0.07
    (Filter
    0.07
    [%
    0.07
    (LOG
    0.07
    
    0.07
    iế
    0.07
     opcion
    0.06
     육
    0.06
    طم
    0.06
     IUser
    0.06
    Activations Density 0.139%

    No Known Activations