© 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. 79954
    Prev
    Next
    INDEX
    Explanations

    opinions and possibilities

    np_max-act · gemini-2.0-flash

    discussions regarding the roles of global and local information in visual perception.

    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
     script
    -0.06
    нов
    -0.06
    larına
    -0.06
    ,input
    -0.06
    _activation
    -0.06
     later
    -0.06
     Doch
    -0.06
     품
    -0.06
     transition
    -0.06
     Packages
    -0.06
    POSITIVE LOGITS
    .getColumnModel
    0.06
    LD
    0.06
    -Benz
    0.06
    VG
    0.06
     Riding
    0.06
     влад
    0.06
     jov
    0.06
    HTTP
    0.06
    -needed
    0.06
    -cor
    0.06
    Activations Density 0.259%

    No Known Activations