© 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. 9031
    Prev
    Next
    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash

    This neuron fires on the wrap-up/conclusion phrasing used when summarizing advice (e.g. “By following these steps…”).

    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
     mmap
    -0.07
     removable
    -0.07
     über
    -0.06
    .cost
    -0.06
     tractor
    -0.06
     compat
    -0.06
     medal
    -0.06
    yas
    -0.06
     квіт
    -0.06
    ь
    -0.06
    POSITIVE LOGITS
     optarg
    0.07
    ån
    0.07
    적인
    0.06
    .".
    0.06
    ความร
    0.06
    ському
    0.06
    .SingleOrDefault
    0.06
    .getModel
    0.06
    +"'
    0.06
     Chr
    0.06
    Activations Density 0.056%

    No Known Activations