© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128670
    Prev
    Next
    INDEX
    Explanations

    aspirin

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of common over-the-counter pain-relief/fever-reducer drug names.

    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
    asions
    -0.07
     WORLD
    -0.07
     Voldemort
    -0.07
     UX
    -0.07
     Net
    -0.07
     mind
    -0.07
    mart
    -0.07
    orts
    -0.07
    _bed
    -0.07
     Rome
    -0.06
    POSITIVE LOGITS
     Yoga
    0.07
    θι
    0.06
     асп
    0.06
     asymmetric
    0.06
    setContent
    0.06
    стати
    0.06
    吸
    0.06
     이는
    0.06
     pás
    0.06
     girişim
    0.06
    Activations Density 0.001%

    No Known Activations