© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12545
    Prev
    Next
    INDEX
    Explanations

    historical records

    np_max-act · gemini-2.0-flash

    The neuron activates on evaluative descriptive phrases that frame something as providing insight or significance—e.g. “valuable source,” “window into,” or “important record.”

    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
     kỳ
    -0.07
    Nodes
    -0.07
    _gr
    -0.07
    672
    -0.06
     yaptığı
    -0.06
    Ups
    -0.06
    "?>↵
    -0.06
     окрем
    -0.06
    Theta
    -0.06
     věci
    -0.06
    POSITIVE LOGITS
     malaria
    0.07
    (Environment
    0.07
     reflective
    0.06
     cleanliness
    0.06
     forth
    0.06
     đ
    0.06
     Scholars
    0.06
    _converter
    0.06
    .animation
    0.06
    =n
    0.06
    Activations Density 0.024%

    No Known Activations