© 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. 55857
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    This neuron detects introductory author-statement phrases that begin a paper’s main contribution (e.g. “In this paper/Letter/work…”).

    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
    ovu
    -0.06
    _fold
    -0.06
    (equal
    -0.06
     repression
    -0.06
    尔
    -0.06
     ocur
    -0.06
     tram
    -0.06
    _ENGINE
    -0.06
    	tx
    -0.06
    _O
    -0.06
    POSITIVE LOGITS
     sincerely
    0.07
    -ng
    0.07
    sat
    0.07
    _reordered
    0.07
    ,dim
    0.06
     timely
    0.06
     proudly
    0.06
     Closed
    0.06
     regul
    0.06
     nik
    0.06
    Activations Density 0.017%

    No Known Activations