© 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
    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. 30440
    Prev
    Next
    INDEX
    Explanations

    group of people

    np_max-act · gemini-2.0-flash

    references to awards and recognition in various fields.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron responds to acknowledgments or expressions of thanks toward groups of people (e.g. “everyone,” “all the staff,” “vendors,” “bankers”) involved in a project.

    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
    .Utils
    -0.07
    iage
    -0.07
     colon
    -0.07
    (crate
    -0.07
     pioneered
    -0.07
    ček
    -0.07
     SET
    -0.07
     Set
    -0.06
    (players
    -0.06
    (observer
    -0.06
    POSITIVE LOGITS
     waivers
    0.06
    []);↵
    0.06
    ="#
    0.06
    iest
    0.06
    ilia
    0.06
     %"
    0.06
    Он
    0.06
     <!--[
    0.06
    ۱۹۹
    0.06
     manufact
    0.06
    Activations Density 0.024%

    No Known Activations