Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 61375
    Prev
    Next
    INDEX
    Explanations

    ,

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.07
    environments
    -0.06
    γων
    -0.06
    سوب
    -0.06
    @section
    -0.06
    Installation
    -0.06
    发布
    -0.06
    ้าหน
    -0.06
    OnClick
    -0.06
    ίος
    -0.06
    POSITIVE LOGITS
     Gujar
    0.07
     år
    0.07
     unconditional
    0.07
     Reading
    0.06
     getPage
    0.06
     mutating
    0.06
     keypad
    0.06
     everyone
    0.06
     aproxim
    0.06
    incer
    0.06
    Activations Density 0.001%

    No Known Activations