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. 11-RESID-POST-AA
    6. 35910
    Prev
    Next
    INDEX
    Explanations

    King

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HQ
    -0.07
    turtle
    -0.06
     lead
    -0.06
     Philips
    -0.06
    asonry
    -0.06
    .shopping
    -0.06
    _TestCase
    -0.06
    _MEDIA
    -0.06
    olar
    -0.06
    Pixmap
    -0.06
    POSITIVE LOGITS
     وش
    0.07
     науч
    0.07
    وجد
    0.06
     competent
    0.06
     dump
    0.06
     об
    0.06
     velké
    0.06
     "";
    0.06
    継
    0.06
    ôte
    0.06
    Activations Density 0.270%

    No Known Activations