© 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. 3-RESID-POST-AA
    11. 94183
    Prev
    Next
    INDEX
    Explanations

    categories and types

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ，而且
    -0.07
    ，這
    -0.07
    .GridView
    -0.07
    ,sizeof
    -0.07
     arrayList
    -0.07
    \Exception
    -0.07
    (getActivity
    -0.07
    .GetAxis
    -0.07
    ，这
    -0.06
     /****************************************************************
    -0.06
    POSITIVE LOGITS
     spices
    0.06
     potatoes
    0.06
     repaired
    0.06
     S
    0.06
     VB
    0.06
    Cap
    0.06
     cherish
    0.06
    -ground
    0.06
    Plant
    0.06
    _slider
    0.06
    Activations Density 0.095%

    No Known Activations