© 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. 51901
    Prev
    Next
    INDEX
    Explanations

    Game beginnings or starting items

    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
     makeshift
    -0.07
    Containers
    -0.06
     Их
    -0.06
     письмен
    -0.06
     همه
    -0.06
    房间
    -0.06
     прев
    -0.06
    �
    -0.06
    òi
    -0.06
     jedno
    -0.06
    POSITIVE LOGITS
    depth
    0.07
    Authorization
    0.07
    /audio
    0.07
    کی
    0.07
    34
    0.06
    oval
    0.06
    -example
    0.06
    .curve
    0.06
    =http
    0.06
     errorMessage
    0.06
    Activations Density 0.004%

    No Known Activations