© 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. 123390
    Prev
    Next
    INDEX
    Explanations

    meter

    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
    toList
    -0.07
     }?>↵
    -0.07
     airy
    -0.06
     Sch
    -0.06
    447
    -0.06
     Trou
    -0.06
     아이콘
    -0.06
    (title
    -0.06
    achines
    -0.06
    psi
    -0.06
    POSITIVE LOGITS
    -operative
    0.08
     RTVF
    0.06
    -template
    0.06
    (CONFIG
    0.06
    [length
    0.06
    rna
    0.06
    raphics
    0.06
    operative
    0.06
     invert
    0.06
     qp
    0.06
    Activations Density 0.003%

    No Known Activations