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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11756
    Prev
    Next
    INDEX
    Explanations

    customers, users, owners

    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
    ávě
    -0.06
     něco
    -0.06
    sets
    -0.06
     yên
    -0.06
    NFL
    -0.06
    shows
    -0.06
     vlád
    -0.06
    Prince
    -0.06
    788
    -0.06
    Studio
    -0.06
    POSITIVE LOGITS
    LAT
    0.07
     lact
    0.06
     DISCLAIMED
    0.06
     рес
    0.06
    /MIT
    0.06
    <decltype
    0.06
    (ListNode
    0.06
    capitalize
    0.06
    уется
    0.06
    prompt
    0.06
    Activations Density 0.055%

    No Known Activations