© 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. 71361
    Prev
    Next
    INDEX
    Explanations

    losing

    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
     GAP
    -0.07
     Jeffrey
    -0.07
     你
    -0.07
     BER
    -0.07
     lemma
    -0.06
     том
    -0.06
     Holy
    -0.06
    .isOpen
    -0.06
    	text
    -0.06
    (Connection
    -0.06
    POSITIVE LOGITS
     Overnight
    0.07
     XD
    0.06
     eg
    0.06
    hani
    0.06
     Markt
    0.06
    striction
    0.06
    洲
    0.06
    ******/↵
    0.06
    ьер
    0.06
    982
    0.06
    Activations Density 0.016%

    No Known Activations