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. 91565
    Prev
    Next
    INDEX
    Explanations

    select

    np_max-act · gemini-2.0-flash

    The neuron flags detailed, step-by-step instructional content or “how-to” sequences.

    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
     onCreateOptionsMenu
    -0.07
    -е
    -0.07
     commodo
    -0.06
    隠
    -0.06
    恨
    -0.06
    mall
    -0.06
     事
    -0.06
    ember
    -0.06
     عبدال
    -0.06
    alertView
    -0.06
    POSITIVE LOGITS
    self
    0.07
    )+'
    0.07
    .primary
    0.07
    /')↵
    0.07
    primary
    0.06
    о
    0.06
    Today
    0.06
    .isArray
    0.06
     craving
    0.06
    _Select
    0.06
    Activations Density 0.010%

    No Known Activations