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. 127837
    Prev
    Next
    INDEX
    Explanations

    uncertain outcomes

    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
    ].'
    -0.06
     مذه
    -0.06
     πα
    -0.06
    /classes
    -0.06
    230
    -0.06
     cabeza
    -0.06
     وجه
    -0.06
     دور
    -0.06
     Trails
    -0.06
    .Bottom
    -0.06
    POSITIVE LOGITS
     removable
    0.07
    _approval
    0.07
    沒
    0.07
     Grat
    0.06
     stationed
    0.06
     implements
    0.06
     Cock
    0.06
    olidays
    0.06
     newPos
    0.06
    laması
    0.06
    Activations Density 0.050%

    No Known Activations