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. 104563
    Prev
    Next
    INDEX
    Explanations

    21

    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
     Miller
    -0.07
     Schro
    -0.06
     deployment
    -0.06
     mill
    -0.06
     Crate
    -0.06
     executor
    -0.06
     Crack
    -0.06
     Mode
    -0.06
     ClassName
    -0.06
     sortOrder
    -0.06
    POSITIVE LOGITS
    21
    0.09
     فارسی
    0.08
    سد
    0.07
    .↵↵↵↵
    0.07
    ção
    0.07
    ök
    0.07
    幸福
    0.07
     mutually
    0.07
    ớ
    0.07
    ENDED
    0.07
    Activations Density 0.019%

    No Known Activations