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. 3-RESID-POST-AA
    6. 94348
    Prev
    Next
    INDEX
    Explanations

    level

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ディース
    -0.07
    acers
    -0.07
     usando
    -0.06
     yyyy
    -0.06
    (Func
    -0.06
    ;//
    -0.06
    φη
    -0.06
    ''''
    -0.06
    MMdd
    -0.06
     عدد
    -0.06
    POSITIVE LOGITS
    .BLL
    0.07
     employers
    0.06
     reinst
    0.06
    opol
    0.06
     resc
    0.06
    particle
    0.06
    73
    0.06
     levels
    0.06
     πα
    0.06
    ทอง
    0.06
    Activations Density 0.012%

    No Known Activations