© 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. 13007
    Prev
    Next
    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash

    The neuron activates on list‐introductory cue phrases (e.g. “include,” “examples of which,” “which include”) that signal the start of an enumeration.

    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
    好
    -0.07
     SV
    -0.06
     invol
    -0.06
    Run
    -0.06
    aupt
    -0.06
     Mar
    -0.06
    STA
    -0.06
     تکن
    -0.06
     threads
    -0.06
     integr
    -0.06
    POSITIVE LOGITS
     которого
    0.07
    which
    0.07
     UITableViewDelegate
    0.06
     สถาน
    0.06
     which
    0.06
    longitude
    0.06
    .fromRGBO
    0.06
     Highlands
    0.06
     timeval
    0.06
    งอย
    0.06
    Activations Density 0.013%

    No Known Activations