© 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. 68666
    Prev
    Next
    INDEX
    Explanations

    code and citations

    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
     зобов
    -0.07
    (IService
    -0.07
    taient
    -0.07
     plata
    -0.07
    StringUtil
    -0.06
    โลก
    -0.06
    .Act
    -0.06
    (Char
    -0.06
    848
    -0.06
     začí
    -0.06
    POSITIVE LOGITS
    	path
    0.07
     Wind
    0.06
     Gren
    0.06
    Wind
    0.06
    oise
    0.06
    
    0.06
     PROT
    0.06
     LOGIN
    0.06
    ROADCAST
    0.06
     Chin
    0.06
    Activations Density 0.000%

    No Known Activations