© 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. 128389
    Prev
    Next
    INDEX
    Explanations

    Introductions and discussions

    np_max-act · gemini-2.0-flash

    chemical compounds involved in the production process of pharmaceuticals and other industrial applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects phrasing that signals an upcoming in-depth examination or overview—e.g. “take a closer look at.”

    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
    INC
    -0.08
     İz
    -0.06
    \Mapping
    -0.06
    _DAMAGE
    -0.06
     評
    -0.06
    IDO
    -0.06
    Dados
    -0.06
    Undo
    -0.06
    .Throw
    -0.06
    igin
    -0.06
    POSITIVE LOGITS
    ();"
    0.07
    \Configuration
    0.06
     exceptionally
    0.06
     added
    0.06
    -range
    0.06
    %↵↵
    0.06
     spec
    0.06
    roc
    0.06
     excessive
    0.06
     epic
    0.06
    Activations Density 0.064%

    No Known Activations