© 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. 7-RESID-POST-AA
    6. 113925
    Prev
    Next
    INDEX
    Explanations

    "pier" and "ier"

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _HELP
    -0.07
     NOTE
    -0.07
    ohn
    -0.06
    '],$
    -0.06
     친
    -0.06
    '}}>
    -0.06
     talent
    -0.06
     Sabha
    -0.06
    	cont
    -0.06
    .day
    -0.06
    POSITIVE LOGITS
     Pier
    0.15
     pier
    0.13
     dock
    0.07
     polar
    0.07
     tri
    0.07
     Official
    0.07
     docks
    0.07
     perc
    0.06
    519
    0.06
     terminates
    0.06
    Activations Density 0.001%

    No Known Activations