© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 98184
    Prev
    Next
    INDEX
    Explanations

    courts

    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
     Computational
    -0.07
     libraries
    -0.07
     computational
    -0.07
    ray
    -0.06
     компании
    -0.06
     slides
    -0.06
    -stat
    -0.06
    morph
    -0.06
    LP
    -0.06
     tế
    -0.06
    POSITIVE LOGITS
    .onDestroy
    0.07
     العرب
    0.06
     نب
    0.06
     incess
    0.06
     endless
    0.06
    ameda
    0.06
    ώς
    0.06
     zahrani
    0.06
    करण
    0.06
     Nail
    0.06
    Activations Density 0.044%

    No Known Activations