© 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. 15-RESID-POST-AA
    6. 58464
    Prev
    Next
    INDEX
    Explanations

    the/to

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thang
    -0.07
     haline
    -0.07
     Grad
    -0.06
    悠
    -0.06
     Building
    -0.06
     contrat
    -0.06
    	vo
    -0.06
    .NOT
    -0.06
     elemento
    -0.06
     LTC
    -0.06
    POSITIVE LOGITS
    enzie
    0.07
     XV
    0.06
    	pstmt
    0.06
     boyfriend
    0.06
    ilded
    0.06
    ывают
    0.06
    .isPresent
    0.06
    B
    0.06
    inant
    0.06
    ۱۷
    0.06
    Activations Density 0.027%

    No Known Activations