© 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. 19-RESID-POST-AA
    6. 73934
    Prev
    Next
    INDEX
    Explanations

    therapeutic treatments

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dance
    -0.06
     skin
    -0.06
     osm
    -0.06
    _io
    -0.06
     İl
    -0.06
     indu
    -0.06
    เตอร
    -0.06
    _operator
    -0.06
     Two
    -0.06
     Private
    -0.06
    POSITIVE LOGITS
    	k
    0.07
     Appalachian
    0.07
    .asarray
    0.06
    �
    0.06
     Tyson
    0.06
    xfb
    0.06
    /sp
    0.06
     kiş
    0.06
    pcb
    0.06
    .router
    0.06
    Activations Density 0.099%

    No Known Activations