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. 9917
    Prev
    Next
    INDEX
    Explanations

    200

    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
     Nobel
    -0.07
    球
    -0.06
     shirts
    -0.06
     集
    -0.06
     Update
    -0.06
     Celebr
    -0.06
     aydın
    -0.06
     Ticket
    -0.06
    __)
    -0.06
    =\""
    -0.06
    POSITIVE LOGITS
     фіз
    0.07
     intervening
    0.07
     Met
    0.06
    'ex
    0.06
    Sub
    0.06
     çerçev
    0.06
     Ін
    0.06
    (contract
    0.06
     nutritional
    0.06
     Classifier
    0.06
    Activations Density 0.008%

    No Known Activations