© 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. 11-RESID-POST-AA
    11. 19923
    Prev
    Next
    INDEX
    Explanations

    drug delivery/biological systems

    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
     कह
    -0.07
    _sku
    -0.07
     Dex
    -0.06
    Ide
    -0.06
     backgrounds
    -0.06
     Paths
    -0.06
     IllegalAccessException
    -0.06
    ежать
    -0.06
     cylinder
    -0.06
     Kosten
    -0.06
    POSITIVE LOGITS
    (rowIndex
    0.07
     {}",
    0.06
     информа
    0.06
    イヤ
    0.06
    py
    0.06
    τζ
    0.06
     organizers
    0.06
     outr
    0.06
    ">#
    0.06
    XmlNode
    0.06
    Activations Density 0.015%

    No Known Activations