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. 15-RESID-POST-AA
    6. 79611
    Prev
    Next
    INDEX
    Explanations

    varied excerpts

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slun
    -0.06
    .XRTableCell
    -0.06
     teď
    -0.06
     '.
    -0.06
    blockquote
    -0.06
     одном
    -0.06
    imei
    -0.06
     пал
    -0.06
     '((
    -0.05
    .[
    -0.05
    POSITIVE LOGITS
     proximity
    0.07
     creator
    0.07
    inance
    0.07
     disruption
    0.07
    (currency
    0.07
     dünyada
    0.07
    ication
    0.07
    ser
    0.06
    ,u
    0.06
    Boss
    0.06
    Activations Density 0.000%

    No Known Activations