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. 27-RESID-POST-AA
    6. 101957
    Prev
    Next
    INDEX
    Explanations

    Bew

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (args
    -0.06
     primer
    -0.06
     konci
    -0.06
    urope
    -0.06
     spep
    -0.06
     skvěl
    -0.06
    OTH
    -0.06
     Tactics
    -0.06
     YY
    -0.06
    PIO
    -0.06
    POSITIVE LOGITS
    �
    0.07
    бы
    0.07
     athleticism
    0.07
    nilai
    0.06
     бума
    0.06
     pokoj
    0.06
    brew
    0.06
    .closePath
    0.06
     kırmızı
    0.06
    shaled
    0.06
    Activations Density 0.001%

    No Known Activations