© 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. 51699
    Prev
    Next
    INDEX
    Explanations

    for

    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
     aşağı
    -0.08
    aly
    -0.06
    ts
    -0.06
    ूक
    -0.06
    ěti
    -0.06
    έ
    -0.06
     bidi
    -0.06
    String
    -0.06
     밀
    -0.06
    IVE
    -0.06
    POSITIVE LOGITS
    Cons
    0.07
    (main
    0.07
     celebr
    0.07
     lonely
    0.07
     '..',
    0.07
     eql
    0.06
    _Category
    0.06
     rue
    0.06
     часа
    0.06
    ción
    0.06
    Activations Density 0.242%

    No Known Activations