© 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. 92071
    Prev
    Next
    INDEX
    Explanations

    business/finance reports

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric and financial‐instrument terms—percentages, note issuances, “Senior Secured Notes,” outstanding amounts, and similar debt‐offering details.

    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
     bert
    -0.07
     charging
    -0.07
    }.{
    -0.06
    (pkt
    -0.06
     LIN
    -0.06
    oài
    -0.06
     Guy
    -0.06
    (IntPtr
    -0.06
    ви
    -0.05
     fed
    -0.05
    POSITIVE LOGITS
     Yield
    0.07
     Ağustos
    0.07
     societies
    0.06
     prá
    0.06
     ข
    0.06
    locked
    0.06
    \Bridge
    0.06
    δό
    0.06
    乘
    0.06
    	callback
    0.06
    Activations Density 0.454%

    No Known Activations