© 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
    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. 124708
    Prev
    Next
    INDEX
    Explanations

    Features and parts

    np_max-act · gemini-2.0-flash

    The neuron flags the generic introductory/background statements you find in technical or patent‐style prose (e.g. opening lines that begin “Various …” or otherwise summarize prior art or context).

    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
     plenty
    -0.08
    Esc
    -0.06
    getSimpleName
    -0.06
     Single
    -0.06
     NOTHING
    -0.06
     konu
    -0.06
     almost
    -0.06
    OCKET
    -0.06
     ekran
    -0.06
    France
    -0.05
    POSITIVE LOGITS
    Ư
    0.07
    hack
    0.07
     может
    0.06
    بات
    0.06
     Он
    0.06
     доктор
    0.06
     рам
    0.06
     WP
    0.06
    _oct
    0.06
     маг
    0.06
    Activations Density 0.180%

    No Known Activations