© 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. 11-RESID-POST-AA
    6. 93381
    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
    idente
    -0.08
    "But
    -0.06
    classCallCheck
    -0.06
    _FF
    -0.06
    یره
    -0.06
    Rank
    -0.06
    “But
    -0.06
    脚
    -0.06
    ert
    -0.06
    со
    -0.06
    POSITIVE LOGITS
     gener
    0.08
    /locale
    0.07
     reloadData
    0.07
    .SelectedItem
    0.07
     genetically
    0.06
     Camel
    0.06
     نی
    0.06
    (payload
    0.06
     Bale
    0.06
     toJSON
    0.06
    Activations Density 0.011%

    No Known Activations