© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 45065
    Prev
    Next
    INDEX
    Explanations

    tracking

    np_max-act · gemini-2.0-flash

    The neuron activates on technical references to tracking or “follow” systems (e.g. auto-tracking, target tracking, follow-me functionality) in device and sensor descriptions.

    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
     adjunct
    -0.07
     мет
    -0.06
    .Action
    -0.06
    迪
    -0.06
     bend
    -0.06
    �
    -0.06
    ,alpha
    -0.06
    δο
    -0.06
    59
    -0.06
     clusters
    -0.06
    POSITIVE LOGITS
     ensuing
    0.07
    новид
    0.07
    介绍
    0.07
     müşter
    0.06
     правило
    0.06
     remainder
    0.06
     entities
    0.06
    ленные
    0.06
    _InitStructure
    0.06
     Repo
    0.06
    Activations Density 0.012%

    No Known Activations