© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 34236
    Prev
    Next
    INDEX
    Explanations

    interrupt

    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
     الطبي
    -0.07
     baths
    -0.06
     imperial
    -0.06
     legislation
    -0.06
     bath
    -0.06
     refresh
    -0.06
     closed
    -0.06
     PRODUCT
    -0.06
     спросил
    -0.06
     denně
    -0.06
    POSITIVE LOGITS
     olacağ
    0.07
    (itemView
    0.06
    fin
    0.06
     jadx
    0.06
     Angry
    0.06
    shint
    0.06
     superclass
    0.06
    "bytes
    0.06
    (operator
    0.06
     bych
    0.06
    Activations Density 0.088%

    No Known Activations