© 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. 44350
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    This neuron strongly fires on high-level instruction or system‐prompt sentences (e.g. “You are a helpful assistant…,” “The codes you can suggest are:,” “You are an android application tester…,” etc.).

    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
    .Format
    -0.07
     airing
    -0.07
     Н
    -0.06
     Ingen
    -0.06
     az
    -0.06
     відвід
    -0.06
     Miy
    -0.06
    .isChecked
    -0.06
     shar
    -0.06
     Sp
    -0.06
    POSITIVE LOGITS
    함
    0.07
    crc
    0.07
     rims
    0.06
    erver
    0.06
    _GET
    0.06
     hype
    0.06
    ıyorum
    0.06
    íž
    0.06
    150
    0.06
     resize
    0.06
    Activations Density 0.035%

    No Known Activations