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. 27-RESID-POST-AA
    6. 73488
    Prev
    Next
    INDEX
    Explanations

    Year

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Preference
    -0.06
    важа
    -0.06
    (",
    -0.06
    Ingredient
    -0.06
    lando
    -0.06
     objs
    -0.06
    .SetKeyName
    -0.06
    ])+
    -0.06
     Va
    -0.06
    ルド
    -0.06
    POSITIVE LOGITS
    eder
    0.07
    Owner
    0.07
    UITableView
    0.06
    ьер
    0.06
    itian
    0.06
    들을
    0.06
    isyon
    0.06
    ทอง
    0.06
     gameOver
    0.06
    spot
    0.06
    Activations Density 0.002%

    No Known Activations