© 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. 15-RESID-POST-AA
    6. 62108
    Prev
    Next
    INDEX
    Explanations

    articles

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     之
    -0.07
     curs
    -0.07
     پرداز
    -0.07
     Бол
    -0.07
     fait
    -0.06
     Є
    -0.06
     個
    -0.06
     Zw
    -0.06
     К
    -0.06
     Буд
    -0.06
    POSITIVE LOGITS
     ISR
    0.07
    .Std
    0.06
    agr
    0.06
     '/
    0.06
     motors
    0.06
    .amazon
    0.06
     curl
    0.06
     Manning
    0.06
    lož
    0.06
    .between
    0.06
    Activations Density 0.161%

    No Known Activations