© 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. 130401
    Prev
    Next
    INDEX
    Explanations

    parency

    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
    _parameter
    -0.06
     Reed
    -0.06
     좌
    -0.06
    _script
    -0.06
     Weapons
    -0.06
    _home
    -0.06
     mayor
    -0.06
     kill
    -0.06
    이터
    -0.06
     beach
    -0.06
    POSITIVE LOGITS
     нього
    0.07
    prec
    0.07
     TokenType
    0.07
    NavController
    0.07
     ej
    0.06
    ueva
    0.06
    卒
    0.06
    \
    0.06
    이스
    0.06
     Jerseys
    0.06
    Activations Density 0.000%

    No Known Activations