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. 25097
    Prev
    Next
    INDEX
    Explanations

    the

    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
    čila
    -0.07
     terrifying
    -0.06
    _vert
    -0.06
    _horizontal
    -0.06
    acute
    -0.06
     staggering
    -0.06
    الع
    -0.06
    .SwingConstants
    -0.06
     ips
    -0.06
     مور
    -0.06
    POSITIVE LOGITS
     addr
    0.07
     đai
    0.07
     Tale
    0.07
    _Msp
    0.07
     guests
    0.07
    стика
    0.07
     problems
    0.07
    _SF
    0.07
    getActiveSheet
    0.06
    =tf
    0.06
    Activations Density 0.096%

    No Known Activations