© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77145
    Prev
    Next
    INDEX
    Explanations

    stalk

    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
     misery
    -0.08
     حول
    -0.07
    __)
    -0.07
     shelves
    -0.07
     _
    ↵
    -0.07
    ised
    -0.06
    REET
    -0.06
    рения
    -0.06
     ();↵↵
    -0.06
    ++;↵↵
    -0.06
    POSITIVE LOGITS
     vo
    0.07
    .Dense
    0.07
    cmc
    0.06
     stalk
    0.06
     scent
    0.06
    avez
    0.06
     쿠
    0.06
    Gray
    0.06
     perk
    0.06
    스크
    0.06
    Activations Density 0.005%

    No Known Activations