© 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. 111763
    Prev
    Next
    INDEX
    Explanations

    -collapse

    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
    her
    -0.07
     thereby
    -0.07
     tiene
    -0.06
     perso
    -0.06
    .Username
    -0.06
    	top
    -0.06
    .vert
    -0.06
     elem
    -0.06
     збір
    -0.06
     없습니다
    -0.06
    POSITIVE LOGITS
    agne
    0.07
    PrivateKey
    0.07
    opot
    0.07
    lasses
    0.07
    optimize
    0.06
     ASS
    0.06
    _Settings
    0.06
    .spi
    0.06
     cough
    0.06
    Particles
    0.06
    Activations Density 0.001%

    No Known Activations