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. 27042
    Prev
    Next
    INDEX
    Explanations

    collateral material

    np_max-act · gemini-2.0-flash

    The neuron flags terms referring to branding deliverables and marketing collateral (e.g. collateral, website, brochures, business cards, promotional materials).

    oai_token-act-pair · o4-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
    _network
    -0.08
    phant
    -0.06
    خرج
    -0.06
     onload
    -0.06
    ernote
    -0.06
    curr
    -0.06
     matt
    -0.06
    恩
    -0.06
    .stub
    -0.06
    ounded
    -0.06
    POSITIVE LOGITS
    Sections
    0.07
    енными
    0.07
     θέ
    0.07
     Forum
    0.06
    Orden
    0.06
     Soda
    0.06
     roads
    0.06
     disposing
    0.06
    \Order
    0.06
     benches
    0.06
    Activations Density 0.016%

    No Known Activations