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. 11-RESID-POST-AA
    6. 94003
    Prev
    Next
    INDEX
    Explanations

    {

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nüfus
    -0.07
    Indented
    -0.06
    丝
    -0.06
    Rachel
    -0.06
    _FAILURE
    -0.06
     Clarke
    -0.06
    Blake
    -0.06
     законодав
    -0.06
    eriod
    -0.06
    ня
    -0.06
    POSITIVE LOGITS
     condemned
    0.07
    _atom
    0.07
    >\<
    0.06
     Facing
    0.06
    เตร
    0.06
    Spell
    0.06
     bills
    0.05
    Ÿ
    0.05
    __(↵
    0.05
     الذين
    0.05
    Activations Density 0.004%

    No Known Activations