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. 122233
    Prev
    Next
    INDEX
    Explanations

    cervical

    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
     दब
    -0.06
     defines
    -0.06
    люб
    -0.06
    Dam
    -0.06
     пром
    -0.06
    ब
    -0.06
    tréal
    -0.06
    .UN
    -0.06
    eea
    -0.06
     satın
    -0.06
    POSITIVE LOGITS
     cerv
    0.11
     cervical
    0.10
     कहन
    0.08
    갑
    0.07
    在地
    0.06
    .addProperty
    0.06
    خرید
    0.06
     cư
    0.06
     dalších
    0.06
    діл
    0.06
    Activations Density 0.003%

    No Known Activations