© 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. 30143
    Prev
    Next
    INDEX
    Explanations

    life

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to occurrences of the word “life” (and its close inflected forms), flagging mentions of “life” or “living.”

    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
    Salt
    -0.07
     Sav
    -0.06
     rice
    -0.06
     pool
    -0.06
    我
    -0.06
    icycle
    -0.06
    Winter
    -0.06
     spikes
    -0.06
     Closed
    -0.06
     discouraged
    -0.06
    POSITIVE LOGITS
     life
    0.09
    生活
    0.08
     Life
    0.07
    ionario
    0.07
     verbally
    0.07
     содерж
    0.07
     hưởng
    0.07
     vida
    0.07
    affen
    0.06
    になり
    0.06
    Activations Density 0.046%

    No Known Activations