© 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. 8761
    Prev
    Next
    INDEX
    Explanations

    python requirements files

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of a requirements file (e.g. “requirements.txt” or the “-r requirements.txt” flag) in pip install commands.

    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
     disgrace
    -0.08
     locator
    -0.06
    _member
    -0.06
    ısız
    -0.06
     søker
    -0.06
     Welcome
    -0.06
    %;↵
    -0.06
    北
    -0.06
    _per
    -0.06
    ıştır
    -0.06
    POSITIVE LOGITS
     terra
    0.08
    排序
    0.07
    ='',
    0.07
     outspoken
    0.07
     Associations
    0.07
     interstate
    0.07
    Tesla
    0.06
    Navig
    0.06
    rbrakk
    0.06
     tactile
    0.06
    Activations Density 0.003%

    No Known Activations