© 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
    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. 126387
    Prev
    Next
    INDEX
    Explanations

    /licenses

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “licenses” in source‐file license header comments.

    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
    Say
    -0.07
    Vict
    -0.07
    Higher
    -0.06
     Glacier
    -0.06
    .str
    -0.06
    司
    -0.06
    /dir
    -0.06
     multiplying
    -0.06
     adresse
    -0.06
     البته
    -0.06
    POSITIVE LOGITS
     �
    0.07
    rome
    0.07
     موسیقی
    0.07
     bios
    0.07
    callback
    0.07
    linkplain
    0.06
    celed
    0.06
    خص
    0.06
    บาล
    0.06
     باعث
    0.06
    Activations Density 0.002%

    No Known Activations