© 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. 129710
    Prev
    Next
    INDEX
    Explanations

    news articles

    np_max-act · gemini-2.0-flash

    discussions around political and economic systems, particularly critiques of governance and policy impact.

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

    The neuron activates on quantitative and temporal expressions, effectively flagging numbers, statistics, and time‐related phrasing in the text.

    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
    inding
    -0.07
     sx
    -0.07
    _p
    -0.06
    ERICA
    -0.06
    按钮
    -0.06
    Fast
    -0.06
    рукту
    -0.06
    439
    -0.06
    anes
    -0.06
    ूड
    -0.06
    POSITIVE LOGITS
    .orm
    0.07
     playbook
    0.07
    |RF
    0.06
    >");
↵
    0.06
     CONSTANTS
    0.06
    .ViewModel
    0.06
    maze
    0.06
    Submitted
    0.06
     ==============================================================
    0.06
    asc
    0.06
    Activations Density 0.070%

    No Known Activations