© 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. 25396
    Prev
    Next
    INDEX
    Explanations

    Making changes and updates

    np_max-act · gemini-2.0-flash

    requests for information or updates related to documentation and formal communication.

    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
     diagnostics
    -0.06
    ecal
    -0.06
    ellers
    -0.06
     ASS
    -0.06
     Neuroscience
    -0.06
    ToBounds
    -0.06
    Self
    -0.05
    (Intent
    -0.05
     cellul
    -0.05
     objetos
    -0.05
    POSITIVE LOGITS
     scaler
    0.07
    IGHT
    0.07
     Late
    0.06
    ight
    0.06
     yanıt
    0.06
     місті
    0.06
     Savaşı
    0.06
    ̀
    0.06
    持ち
    0.06
    <{
    0.06
    Activations Density 0.077%

    No Known Activations