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

    Neuronpedia

    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. 110755
    Prev
    Next
    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash

    The neuron detects words and short phrases that indicate physical locations or settings (e.g. “in,” “outside,” “at,” along with locale nouns like “classroom” or “laboratory”).

    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
     смесь
    -0.08
    нич
    -0.07
    reat
    -0.06
    _greater
    -0.06
    ок
    -0.06
    qc
    -0.06
     手机
    -0.06
     ou
    -0.06
    resource
    -0.06
    แ
    -0.06
    POSITIVE LOGITS
     mama
    0.06
    oài
    0.06
    (mut
    0.06
    Localized
    0.06
    (room
    0.06
     jednání
    0.06
    tracker
    0.06
    LA
    0.06
     اس
    0.06
     مبانی
    0.06
    Activations Density 0.075%

    No Known Activations