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. 19-RESID-POST-AA
    6. 105085
    Prev
    Next
    INDEX
    Explanations

    Variety of topics

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     方法
    -0.07
    ._
    -0.07
     Orders
    -0.07
    ेल
    -0.07
     toolbox
    -0.06
     politician
    -0.06
    ---
    -0.06
     guiding
    -0.06
    国の
    -0.06
     Terrace
    -0.06
    POSITIVE LOGITS
    Sdk
    0.07
    .setHorizontalAlignment
    0.06
    ิถ
    0.06
     demeanor
    0.06
    entina
    0.06
    .rollback
    0.06
     mariage
    0.06
     detach
    0.06
     ağaç
    0.06
     aff
    0.06
    Activations Density 0.000%

    No Known Activations