© 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. 126101
    Prev
    Next
    INDEX
    Explanations

    dark

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the term “dark matter.”

    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
     nxt
    -0.06
    label
    -0.06
    zl
    -0.06
     بت
    -0.06
    克
    -0.06
    )))))↵
    -0.06
     conductor
    -0.06
    动生成
    -0.06
    .CompilerServices
    -0.06
     الك
    -0.06
    POSITIVE LOGITS
    145
    0.07
    .Helpers
    0.06
     Org
    0.06
    ряду
    0.06
     작업
    0.06
     handicap
    0.06
     Chapters
    0.06
     Installer
    0.06
    dfs
    0.06
     Alg
    0.06
    Activations Density 0.002%

    No Known Activations