© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57478
    Prev
    Next
    INDEX
    Explanations

    code related to networking

    np_max-act · gemini-2.0-flash

    networking-related terms and parameters.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects fragments of all-caps IP socket option constant names (e.g. IP_MULTICAST_IF) in code.

    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
    (response
    -0.06
    istem
    -0.06
    公告
    -0.06
     officers
    -0.06
     manufactured
    -0.06
    .querySelector
    -0.06
    ็็
    -0.05
    .docs
    -0.05
    _Register
    -0.05
     pistols
    -0.05
    POSITIVE LOGITS
     kk
    0.07
     nabízí
    0.07
     stringBy
    0.07
     тер
    0.06
    ับต
    0.06
    -rad
    0.06
     Constit
    0.06
     addTarget
    0.06
    .TypeString
    0.06
    	Page
    0.06
    Activations Density 0.001%

    No Known Activations