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. 88823
    Prev
    Next
    INDEX
    Explanations

    computer servers & running them

    np_max-act · gemini-2.0-flash

    The neuron fires on imperative/setup action verbs and terms related to installing, starting, or running services (e.g. “run,” “serve,” “install,” “server”).

    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
    clients
    -0.07
    fields
    -0.07
    tod
    -0.07
     entertainment
    -0.07
     wei
    -0.07
    _damage
    -0.07
     территор
    -0.06
    (queue
    -0.06
    _SET
    -0.06
    photos
    -0.06
    POSITIVE LOGITS
     Ips
    0.07
    ‍
    0.06
    ="")↵
    0.06
     Navigate
    0.06
     '_'
    0.06
     Rule
    0.06
     showModal
    0.06
    <body
    0.06
    olumn
    0.06
    (bool
    0.06
    Activations Density 0.040%

    No Known Activations