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. 122801
    Prev
    Next
    INDEX
    Explanations

    be

    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
     boxes
    -0.07
     likely
    -0.07
    LOUD
    -0.07
     Boxes
    -0.06
     الشي
    -0.06
     Tucson
    -0.06
     جديد
    -0.06
     share
    -0.06
     surgeries
    -0.06
    Checker
    -0.06
    POSITIVE LOGITS
     Ibn
    0.09
     Svens
    0.07
     Codes
    0.07
    N
    0.06
     Nested
    0.06
     gdy
    0.06
     ieee
    0.06
     Nacht
    0.06
     specialties
    0.06
    бра
    0.06
    Activations Density 0.005%

    No Known Activations