© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9013
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron activates on opening and closing parentheses.

    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
     merge
    -0.07
     connectivity
    -0.06
    って
    -0.06
     Apollo
    -0.06
    放在
    -0.06
     sıras
    -0.06
    ことは
    -0.06
    .endswith
    -0.06
    олько
    -0.06
     sticks
    -0.06
    POSITIVE LOGITS
    三
    0.07
    _RGCTX
    0.07
    modifier
    0.07
    .Description
    0.07
    /logs
    0.06
    RegularExpression
    0.06
    @Autowired
    0.06
     nors
    0.06
    :UIControlStateNormal
    0.06
    /music
    0.06
    Activations Density 0.005%

    No Known Activations