© 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. 7-RESID-POST-AA
    11. 34597
    Prev
    Next
    INDEX
    Explanations

    university research/extension

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.07
     بر
    -0.07
    ْه
    -0.06
    採
    -0.06
     Schema
    -0.06
    NewLabel
    -0.06
     заболева
    -0.06
    iven
    -0.06
     triples
    -0.06
    шая
    -0.06
    POSITIVE LOGITS
     problema
    0.07
    =key
    0.07
     ihtiyaç
    0.06
     timeless
    0.06
    毕业
    0.06
    />.↵
    0.06
    織
    0.06
     dua
    0.06
     afect
    0.06
     çap
    0.06
    Activations Density 0.014%

    No Known Activations