© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 125227
    Prev
    Next
    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash

    The neuron detects JavaScript object property names and structure typical of a Webpack configuration (e.g. `module.exports`, `entry`, `output`, `module`, `rules`, `loader` etc.).

    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
    sf
    -0.08
    thers
    -0.07
    quer
    -0.07
     crops
    -0.07
    _LAYOUT
    -0.06
    Equals
    -0.06
     yani
    -0.06
     موجود
    -0.06
     "{}
    -0.06
    hev
    -0.06
    POSITIVE LOGITS
    Partner
    0.07
     plain
    0.07
     zvyš
    0.06
     COPY
    0.06
    ์↵
    0.06
     Ips
    0.06
    /Test
    0.06
    .PostMapping
    0.06
     să
    0.06
     ніч
    0.06
    Activations Density 0.002%

    No Known Activations