© 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. 32495
    Prev
    Next
    INDEX
    Explanations

    NONINFRINGMENT

    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
     chụp
    -0.07
    ีโ
    -0.06
    	connect
    -0.06
    맹
    -0.06
    專
    -0.06
    くらい
    -0.06
    .encrypt
    -0.06
    (resource
    -0.06
    盟
    -0.06
    .JWT
    -0.06
    POSITIVE LOGITS
    .vaadin
    0.07
     Catalan
    0.07
     Recreation
    0.06
    jos
    0.06
     سریال
    0.06
    ]^
    0.06
     defaultCenter
    0.06
     Affero
    0.06
     garage
    0.06
    gress
    0.06
    Activations Density 0.001%

    No Known Activations