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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126109
    Prev
    Next
    INDEX
    Explanations

    affect

    np_max-act · gemini-2.0-flash

    The neuron fires whenever it sees the root “affect” (in words like “affect” or “affecting”), flagging instances of that term.

    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
    Third
    -0.07
     Burton
    -0.07
     ヽ
    -0.07
     Kons
    -0.06
     tijd
    -0.06
     Liverpool
    -0.06
     Orange
    -0.06
     libro
    -0.06
     first
    -0.06
    that
    -0.06
    POSITIVE LOGITS
     affect
    0.11
     affects
    0.11
     affecting
    0.10
     affected
    0.08
    cef
    0.07
    .calendar
    0.07
     influence
    0.07
     inhabit
    0.07
    esis
    0.07
     impacting
    0.06
    Activations Density 0.022%

    No Known Activations