© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 269
    Prev
    Next
    INDEX
    Explanations

    Code/legal/technical language

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ออก
    -0.09
     increment
    -0.06
     igual
    -0.06
    (stream
    -0.06
    AccountId
    -0.06
    -place
    -0.06
    architecture
    -0.06
     retorn
    -0.06
    _GRAPH
    -0.06
     otras
    -0.06
    POSITIVE LOGITS
    .BorderSide
    0.06
     koup
    0.06
    κ
    0.06
     getResources
    0.06
    /use
    0.06
     систем
    0.06
     económ
    0.06
    .MenuStrip
    0.06
     Richardson
    0.06
     Kai
    0.06
    Activations Density 0.000%

    No Known Activations