Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 42222
    Prev
    Next
    INDEX
    Explanations

    Foundation

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the “NET Foundation” string in license/copyright headers.

    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
    аф
    -0.07
     cata
    -0.07
    )،
    -0.07
     различных
    -0.06
    られている
    -0.06
    ابه
    -0.06
    лег
    -0.06
     카
    -0.06
    уй
    -0.06
    大小
    -0.06
    POSITIVE LOGITS
    Industry
    0.07
     Evidence
    0.07
    complete
    0.07
     foundation
    0.07
    /Peak
    0.06
    _box
    0.06
    Copyright
    0.06
     castle
    0.06
     Peer
    0.06
    .series
    0.06
    Activations Density 0.000%

    No Known Activations