© 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. 8950
    Prev
    Next
    INDEX
    Explanations

    neuroscience or neurochemistry

    np_max-act · gemini-2.0-flash

    references to dopamine-related mechanisms and functions in the context of neurological studies.

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

    The neuron selectively responds to mentions of the dopamine‐synthesizing enzyme “tyrosine hydroxylase.”

    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
     Кар
    -0.06
    erif
    -0.06
     movie
    -0.06
    Administrator
    -0.06
    cliente
    -0.06
     Sand
    -0.06
    Speaker
    -0.06
    Len
    -0.06
    ülük
    -0.06
     DVD
    -0.06
    POSITIVE LOGITS
     oluyor
    0.07
    (isset
    0.06
     лі
    0.06
    .Section
    0.06
    (ERROR
    0.06
    .args
    0.06
    .logged
    0.06
    (Double
    0.06
    (CONFIG
    0.06
     выдел
    0.06
    Activations Density 0.001%

    No Known Activations