© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 915
    Prev
    Next
    INDEX
    Explanations

    Code/API snippets

    np_max-act · gemini-2.0-flash

    This neuron detects asynchronous‐call patterns in code (e.g. “With…Chan,” “Async,” “asynchronously,” channel usage).

    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
     forwarded
    -0.07
    读
    -0.07
     ranked
    -0.07
     antibiotic
    -0.07
     Woodward
    -0.07
     comenz
    -0.07
    (sk
    -0.06
    724
    -0.06
     KP
    -0.06
     STORE
    -0.06
    POSITIVE LOGITS
    vrir
    0.07
    verture
    0.06
    buch
    0.06
    имо
    0.06
     networking
    0.06
    овий
    0.06
    すべて
    0.06
     αρ
    0.06
    омен
    0.06
    =*/
    0.06
    Activations Density 0.004%

    No Known Activations