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. 102152
    Prev
    Next
    INDEX
    Explanations

    non-English or code words

    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
    theme
    -0.07
    CONNECT
    -0.06
    en
    -0.06
     '[
    -0.06
     ""))↵
    -0.06
     Collapse
    -0.06
    ец
    -0.06
     hiking
    -0.06
    _numbers
    -0.06
    046
    -0.06
    POSITIVE LOGITS
     BrowserAnimationsModule
    0.07
    antro
    0.07
    ájem
    0.07
     مادر
    0.06
     headed
    0.06
    (SQLException
    0.06
    ạo
    0.06
     나타
    0.06
     về
    0.06
    _HC
    0.06
    Activations Density 0.016%

    No Known Activations