© 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. 942
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash

    This neuron activates on Windows “WdsTransportClient…” API function and related identifier names (e.g. AddRefBuffer, CancelSession, QueryStatus, etc.).

    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
    เจ
    -0.08
     appar
    -0.07
    デ
    -0.07
     Mé
    -0.06
     Visitors
    -0.06
     Cycling
    -0.06
     mejores
    -0.06
    enario
    -0.06
    .init
    -0.06
    .addr
    -0.06
    POSITIVE LOGITS
     strSQL
    0.08
     pprint
    0.07
     مطال
    0.06
    .Refresh
    0.06
    agic
    0.06
     순간
    0.06
    گونه
    0.06
    �
    0.06
     kâ
    0.06
     pinterest
    0.06
    Activations Density 0.012%

    No Known Activations