© 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. 87003
    Prev
    Next
    INDEX
    Explanations

    (

    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
     examples
    -0.06
     OB
    -0.06
    ٬
    -0.06
    _URI
    -0.06
    uştur
    -0.06
    坐
    -0.06
     surroundings
    -0.06
     typical
    -0.06
     vote
    -0.06
    (actor
    -0.06
    POSITIVE LOGITS
    	EIF
    0.07
    manufacturer
    0.06
    escal
    0.06
    ongo
    0.06
    _correction
    0.06
    celik
    0.06
    /person
    0.06
     ngOn
    0.06
    peer
    0.06
    ;q
    0.06
    Activations Density 0.021%

    No Known Activations