© 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. 126102
    Prev
    Next
    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash

    This neuron responds to Microsoft COM/DirectX-style HRESULT calls and related smart-pointer or error-checking macros.

    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
     difficult
    -0.06
    .articles
    -0.06
    Distribution
    -0.06
     encrypt
    -0.06
     Latest
    -0.06
    iddles
    -0.06
     rifle
    -0.06
     other
    -0.06
     saldır
    -0.06
     inquiry
    -0.06
    POSITIVE LOGITS
     ре
    0.07
     국제
    0.07
    //---------------------------------------------------------------------------↵↵
    0.07
    纯
    0.07
    鼻
    0.06
    zeń
    0.06
    _CAL
    0.06
    (gcf
    0.06
    .CommandType
    0.06
     застав
    0.06
    Activations Density 0.012%

    No Known Activations