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. 11-RESID-POST-AA
    6. 75690
    Prev
    Next
    INDEX
    Explanations

    location

    np_max-act · gemini-2.0-flash

    specific details regarding a company's location, establishment, and range of products.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     проб
    -0.07
    count
    -0.07
     stern
    -0.06
    ermint
    -0.06
     encyclopedia
    -0.06
    .Root
    -0.06
    甚
    -0.06
     KY
    -0.06
     perfected
    -0.06
    aton
    -0.06
    POSITIVE LOGITS
    Ан
    0.07
    .bg
    0.07
    ैं.
    0.06
     Birds
    0.06
    -bg
    0.06
     Cities
    0.06
     На
    0.06
    纪
    0.06
     ''.
    0.06
     bestimm
    0.06
    Activations Density 0.004%

    No Known Activations