© 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. 53017
    Prev
    Next
    INDEX
    Explanations

    i or this

    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_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
     créer
    -0.07
     measurable
    -0.07
    Bern
    -0.07
     Kon
    -0.06
    egot
    -0.06
    OLON
    -0.06
     Lok
    -0.06
    andex
    -0.06
    beck
    -0.06
     Bez
    -0.06
    POSITIVE LOGITS
    amera
    0.07
    籍
    0.06
    _AC
    0.06
     Escort
    0.06
    (hw
    0.06
     {
↵
↵
↵
    0.06
    现在
    0.06
    (Fl
    0.06
    alls
    0.06
    ilight
    0.06
    Activations Density 0.001%

    No Known Activations