© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 77587
    Prev
    Next
    INDEX
    Explanations

    language/grammar

    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
    aporation
    -0.07
    (read
    -0.07
    Twenty
    -0.07
    ancellation
    -0.06
    _BUFFER
    -0.06
    (fields
    -0.06
    entů
    -0.06
     cottage
    -0.06
    .daily
    -0.06
     Germany
    -0.06
    POSITIVE LOGITS
    enza
    0.06
     رئيس
    0.06
     sadly
    0.06
    -->
    0.06
    roe
    0.06
    .ItemsSource
    0.06
     близ
    0.06
     λέ
    0.06
    HWND
    0.06
    datatype
    0.06
    Activations Density 0.022%

    No Known Activations