© 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. 109671
    Prev
    Next
    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “License” (i.e. license‐header markers) in source‐code comments and metadata.

    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
    ')}}"
    -0.06
     Lev
    -0.06
    ايل
    -0.06
     ils
    -0.06
    .bc
    -0.06
    -com
    -0.06
    ären
    -0.06
     Ấ
    -0.06
    ?v
    -0.06
     foods
    -0.05
    POSITIVE LOGITS
    cycles
    0.06
    (InputStream
    0.06
    もり
    0.06
     Libraries
    0.06
    �
    0.06
     discipline
    0.06
     Needed
    0.06
    няя
    0.06
    txn
    0.06
     eagle
    0.06
    Activations Density 0.002%

    No Known Activations