© 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. 8791
    Prev
    Next
    INDEX
    Explanations

    scientific procedures

    np_max-act · gemini-2.0-flash

    The neuron activates on and thus detects named entities like vendor or manufacturer names and location abbreviations (e.g., company suppliers, catalog sources, and geographic identifiers).

    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
    _cv
    -0.06
    /ajax
    -0.06
    _PRESS
    -0.06
     shampoo
    -0.06
    गर
    -0.06
    :a
    -0.06
     MainMenu
    -0.06
     nodeList
    -0.06
     음악
    -0.06
    839
    -0.06
    POSITIVE LOGITS
     fund
    0.07
     ith
    0.06
     sovereignty
    0.06
    >";↵
    0.06
     shootout
    0.06
    ;margin
    0.06
     disputed
    0.06
    mobile
    0.06
     vaccinated
    0.06
    soon
    0.06
    Activations Density 0.002%

    No Known Activations