© 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. 115964
    Prev
    Next
    INDEX
    Explanations

    .decode

    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
     Structure
    -0.07
    彼
    -0.07
     Year
    -0.07
     SPACE
    -0.06
     avoiding
    -0.06
    space
    -0.06
     Confidence
    -0.06
     Offer
    -0.06
    iph
    -0.06
     critics
    -0.06
    POSITIVE LOGITS
    .Tipo
    0.08
     nghỉ
    0.07
    드는
    0.07
    .restaurant
    0.07
     getUsername
    0.07
    .DisplayName
    0.06
    .visual
    0.06
    ,color
    0.06
     plunder
    0.06
     ozone
    0.06
    Activations Density 0.002%

    No Known Activations