© 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. 109885
    Prev
    Next
    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash

    The neuron responds to the occurrence of the word “complete,” i.e. it detects that specific imperative verb.

    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
     tor
    -0.07
    SKIP
    -0.07
     IMF
    -0.06
     gzip
    -0.06
     traps
    -0.06
    .info
    -0.06
     плю
    -0.06
    ano
    -0.06
    ۵۰
    -0.06
    .regex
    -0.06
    POSITIVE LOGITS
     diplomatic
    0.06
    è
    0.06
    acter
    0.06
     visuals
    0.06
    』（
    0.06
     campaign
    0.06
    iag
    0.06
     livelihood
    0.06
    urrect
    0.06
     Ec
    0.06
    Activations Density 0.001%

    No Known Activations