Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 122089
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    -ex
    -0.07
    ')↵↵
    -0.07
    تماد
    -0.07
     Speaking
    -0.06
     cake
    -0.06
    prefix
    -0.06
     Universal
    -0.06
    치를
    -0.06
     Zug
    -0.06
    )reader
    -0.06
    POSITIVE LOGITS
     araştır
    0.06
    esini
    0.06
     축구
    0.06
     collabor
    0.06
     नगर
    0.06
     گوشی
    0.06
    ouncill
    0.06
    igated
    0.06
     Garmin
    0.06
    лина
    0.06
    Activations Density 0.031%

    No Known Activations