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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65520
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on occurrences of the word “permit,” as seen in open-source license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    programming-related legal terms and conditions.

    oai_token-act-pair · gpt-4o-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
    ILD
    -0.07
    .course
    -0.06
    ák
    -0.06
    řes
    -0.06
    DataReader
    -0.06
    olds
    -0.06
    IBUT
    -0.06
     Пов
    -0.06
    ainty
    -0.06
     کو
    -0.06
    POSITIVE LOGITS
     Quart
    0.07
    ..
    0.06
     hoàn
    0.06
    titulo
    0.06
    ภ
    0.06
     tho
    0.06
     grinding
    0.06
     adult
    0.06
    ERVED
    0.06
    207
    0.06
    Activations Density 0.001%

    No Known Activations