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. 11-RESID-POST-AA
    6. 50830
    Prev
    Next
    INDEX
    Explanations

    Equations, formulas

    np_max-act · gemini-2.0-flash

    calculations related to expected returns in financial portfolios.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
     religions
    -0.06
     �
    -0.06
     Nas
    -0.06
     LIGHT
    -0.06
     تبلی
    -0.06
    _IN
    -0.06
     Dal
    -0.06
    .Zip
    -0.06
     Nicola
    -0.06
     Store
    -0.06
    POSITIVE LOGITS
    featured
    0.06
     deren
    0.06
    Pink
    0.06
    ตะว
    0.06
    โรค
    0.06
     consistently
    0.06
     دقیق
    0.06
    #ifndef
    0.06
    .',
    0.06
    ienie
    0.06
    Activations Density 0.010%

    No Known Activations