© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 862
    Prev
    Next
    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash

    This neuron detects proper names and named entities—particularly the names of people, teams, boats, and other capitalized titles.

    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
     lineman
    -0.07
     laps
    -0.07
     advertiser
    -0.07
     keyboard
    -0.07
    _PAIR
    -0.06
     Мак
    -0.06
    interp
    -0.06
     IH
    -0.06
    imas
    -0.06
    hos
    -0.06
    POSITIVE LOGITS
     antic
    0.07
     Tên
    0.07
     invis
    0.07
     tisk
    0.07
    Calculator
    0.06
     elek
    0.06
    		↵		↵		↵
    0.06
     영
    0.06
    (sw
    0.06
    .Sm
    0.06
    Activations Density 0.016%

    No Known Activations