© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 103591
    Prev
    Next
    INDEX
    Explanations

    formulation

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	H
    -0.07
     knowledge
    -0.07
     topology
    -0.06
     Assets
    -0.06
     traces
    -0.06
    ('@
    -0.06
     cheese
    -0.06
    ジ
    -0.06
    移
    -0.06
     tapes
    -0.06
    POSITIVE LOGITS
     Cơ
    0.07
     tướng
    0.07
    NSInteger
    0.07
     조선
    0.07
    改革
    0.07
     Conor
    0.06
    .setOutput
    0.06
     Ně
    0.06
    mighty
    0.06
     Phương
    0.06
    Activations Density 0.019%

    No Known Activations