© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75053
    Prev
    Next
    INDEX
    Explanations

    Numbers and code

    np_max-act · gemini-2.0-flash

    address variations, ensuring correct formatting and usage of abbreviations or expansions for location names while retaining the postal code.

    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
    .te
    -0.07
     Concepts
    -0.06
    ctr
    -0.06
    월
    -0.06
     Σχ
    -0.06
    wegian
    -0.06
    Networking
    -0.06
     ดร
    -0.06
     profil
    -0.06
     спроб
    -0.06
    POSITIVE LOGITS
    .identifier
    0.06
     horizontal
    0.06
     contagious
    0.06
    oise
    0.06
    rition
    0.06
     gaan
    0.06
    问题
    0.06
    fx
    0.06
    .reject
    0.06
    @FXML
    0.06
    Activations Density 0.021%

    No Known Activations