© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91684
    Prev
    Next
    INDEX
    Explanations

    Money and percentages

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric share‐split or percentage expressions (e.g. “50/50,” “20%,” etc.) that describe how revenue or funds are divided.

    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
    Unlock
    -0.07
    antar
    -0.06
     realizes
    -0.06
    台
    -0.06
     очі
    -0.06
    -0.06
    _order
    -0.06
     ц
    -0.06
    Shipping
    -0.06
    _spawn
    -0.06
    POSITIVE LOGITS
    (Activity
    0.07
    dyn
    0.07
     Δεν
    0.07
    .extent
    0.06
    .sn
    0.06
    pick
    0.06
    ('//
    0.06
     expertise
    0.06
     jedno
    0.06
    ι
    0.06
    Activations Density 0.017%

    No Known Activations