© 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. 30845
    Prev
    Next
    INDEX
    Explanations

    consider

    np_max-act · gemini-2.0-flash

    This neuron detects the occurrence of the verb “consider” (especially in phrases like “we consider …”) that introduces the topic or focus of a section.

    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
    _stride
    -0.07
    ({},
    -0.07
    然而
    -0.07
    HOW
    -0.07
    StateChanged
    -0.07
     fortified
    -0.06
    *&
    -0.06
    Tell
    -0.06
     answers
    -0.06
     whopping
    -0.06
    POSITIVE LOGITS
    �
    0.06
    :///
    0.06
     mají
    0.06
    cisi
    0.06
    lib
    0.06
    customers
    0.06
     SMB
    0.06
     spoj
    0.06
     ATM
    0.06
    ifference
    0.06
    Activations Density 0.015%

    No Known Activations