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. 19-RESID-POST-AA
    6. 59902
    Prev
    Next
    INDEX
    Explanations

    get

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _than
    -0.07
    -dis
    -0.07
    /fontawesome
    -0.07
    odní
    -0.07
     mas
    -0.07
     caste
    -0.07
    _FAILURE
    -0.07
    ربه
    -0.07
    编号
    -0.07
    ables
    -0.07
    POSITIVE LOGITS
     implication
    0.06
     *)↵
    0.06
    큼
    0.06
     ordinances
    0.06
    ในช
    0.06
    MITTED
    0.05
    .AdapterView
    0.05
     Lexington
    0.05
     GA
    0.05
    .Post
    0.05
    Activations Density 0.130%

    No Known Activations