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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8667
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    code snippets or declarations related to programming.

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

    This neuron fires on snippets of imperative JavaScript code—specifically on jQuery-style method chains involving “.each(…)” and related DOM-traversal/handler calls.

    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
    Cele
    -0.06
    pack
    -0.06
    _sw
    -0.06
    ENN
    -0.06
    Davis
    -0.06
     fixture
    -0.06
    マ
    -0.06
    325
    -0.06
    one
    -0.06
    ONE
    -0.06
    POSITIVE LOGITS
    jekt
    0.07
     ae
    0.07
     квіт
    0.07
    GRADE
    0.06
     εί
    0.06
     krb
    0.06
    _generation
    0.06
    ct
    0.06
    .hours
    0.06
     kred
    0.06
    Activations Density 0.160%

    No Known Activations