© 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. 19-RESID-POST-AA
    11. 10805
    Prev
    Next
    INDEX
    Explanations

    advantage

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ();
↵
    -0.07
    (address
    -0.07
    �
    -0.07
     colleague
    -0.07
    .toolbar
    -0.07
     prospect
    -0.06
    ˆ
    -0.06
    ки
    -0.06
    циклоп
    -0.06
    示
    -0.06
    POSITIVE LOGITS
     casc
    0.07
     зуп
    0.07
    ऊ
    0.06
     nær
    0.06
    ."[
    0.06
    _PUS
    0.06
    teborg
    0.06
     få
    0.06
    News
    0.05
    اون
    0.05
    Activations Density 0.136%

    No Known Activations