© 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. 91628
    Prev
    Next
    INDEX
    Explanations

    professional topics

    np_max-act · gemini-2.0-flash

    The neuron consistently fires on the key noun in technical compound phrases—e.g. “content” in “digital content,” “security” in “data security,” and “management” in “data management.”

    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
     sequential
    -0.06
     dai
    -0.06
    .copy
    -0.06
    ichen
    -0.06
    飯
    -0.06
    登場
    -0.06
     ints
    -0.06
     CrossAxisAlignment
    -0.06
     sequentially
    -0.06
     predictable
    -0.06
    POSITIVE LOGITS
    +'\
    0.06
    PROCESS
    0.06
    519
    0.06
    sage
    0.06
    Comparer
    0.06
    mn
    0.06
     diệt
    0.06
    .crm
    0.06
    Markers
    0.06
    _am
    0.06
    Activations Density 0.106%

    No Known Activations