Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 54007
    Prev
    Next
    INDEX
    Explanations

    sticks

    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
     knitting
    -0.06
     HTML
    -0.06
    「你
    -0.06
    #index
    -0.06
    setStatus
    -0.06
    aters
    -0.05
    쳐
    -0.05
     DROP
    -0.05
     stories
    -0.05
    idence
    -0.05
    POSITIVE LOGITS
    .gradient
    0.07
    <pcl
    0.07
    .cond
    0.07
    Kenn
    0.07
    eking
    0.06
     Seed
    0.06
    eyer
    0.06
     gameplay
    0.06
    २
    0.06
    DECL
    0.06
    Activations Density 0.016%

    No Known Activations