© 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. 11-RESID-POST-AA
    6. 104607
    Prev
    Next
    INDEX
    Explanations

    small

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .wh
    -0.07
    ียวก
    -0.07
    sequent
    -0.07
    _of
    -0.06
     shutter
    -0.06
    ISS
    -0.06
     father
    -0.06
     Similar
    -0.06
     Поч
    -0.06
    گیری
    -0.06
    POSITIVE LOGITS
    outil
    0.07
    eway
    0.06
     contempt
    0.06
    TextInput
    0.06
    ittings
    0.06
    GIN
    0.06
     Minor
    0.06
    	Action
    0.06
     Sang
    0.06
     плани
    0.06
    Activations Density 0.038%

    No Known Activations