© 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. 6330
    Prev
    Next
    INDEX
    Explanations

    code characters

    np_max-act · gemini-2.0-flash

    commands and instructions for executing specific tasks related to managing and analyzing information.

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

    The neuron fires on the names of defined commands (and their argument keys) in the instruction blocks.

    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
    perimental
    -0.06
    	service
    -0.06
     latency
    -0.06
     wurde
    -0.06
     CancellationToken
    -0.06
     Нет
    -0.06
    _variant
    -0.06
     quoting
    -0.06
     нек
    -0.06
    .='
    -0.06
    POSITIVE LOGITS
     Μά
    0.06
    基于
    0.06
     cartoons
    0.06
     roz
    0.06
     září
    0.06
    �
    0.06
     вариант
    0.06
     �
    0.06
    šlo
    0.06
     história
    0.06
    Activations Density 0.003%

    No Known Activations