© 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. 123345
    Prev
    Next
    INDEX
    Explanations

    }

    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
    620
    -0.06
     preamble
    -0.06
    CLLocation
    -0.06
    _make
    -0.06
    ifferential
    -0.06
    -command
    -0.06
     nationalists
    -0.06
     expects
    -0.06
    RequestId
    -0.06
    _AD
    -0.06
    POSITIVE LOGITS
     Financing
    0.07
    ��
    0.07
     Thermal
    0.06
     ल
    0.06
     Comput
    0.06
    .ACT
    0.06
     Classics
    0.06
    ưở
    0.06
     thermal
    0.06
     campaigned
    0.06
    Activations Density 0.060%

    No Known Activations