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. 23-RESID-POST-AA
    6. 103795
    Prev
    Next
    INDEX
    Explanations

    difficulties

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gzip
    -0.06
    (forKey
    -0.06
    NavItem
    -0.06
     landscape
    -0.06
     Kingdom
    -0.06
     Midlands
    -0.06
     Creatures
    -0.06
     productivity
    -0.06
     SceneManager
    -0.06
     Norway
    -0.06
    POSITIVE LOGITS
    (images
    0.07
     nak
    0.07
    Tele
    0.07
    ك
    0.07
    .Persistence
    0.06
    SH
    0.06
    peng
    0.06
    <pcl
    0.06
     Bh
    0.06
     dolu
    0.06
    Activations Density 0.081%

    No Known Activations