© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 123649
    Prev
    Next
    INDEX
    Explanations

    closed

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersistence
    -0.08
    оги
    -0.07
    aptive
    -0.07
    .parameter
    -0.07
    ่อย
    -0.07
    .builders
    -0.07
    ону
    -0.07
    deposit
    -0.07
     発
    -0.07
    $L
    -0.06
    POSITIVE LOGITS
     closed
    0.08
    .Ch
    0.07
     число
    0.06
     features
    0.06
     Genetics
    0.06
    _RDWR
    0.06
     failed
    0.06
     bin
    0.06
     IMF
    0.05
    closed
    0.05
    Activations Density 0.003%

    No Known Activations