© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 32580
    Prev
    Next
    INDEX
    Explanations

    Jones

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _aes
    -0.08
     empleado
    -0.06
     quelle
    -0.06
    许
    -0.06
    _SOL
    -0.06
    _updates
    -0.06
    ugas
    -0.06
     aging
    -0.06
     exist
    -0.06
    єте
    -0.06
    POSITIVE LOGITS
    $key
    0.07
     naj
    0.06
    _browser
    0.06
     правиль
    0.06
     Verm
    0.06
     Chocolate
    0.06
     onChangeText
    0.06
     /*!<
    0.06
    ETHER
    0.06
    taxonomy
    0.06
    Activations Density 0.014%

    No Known Activations