© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 42679
    Prev
    Next
    INDEX
    Explanations

    Formatting numbers with leading zeros

    np_max-act · gemini-2.0-flash

    The neuron fires on lines of literal code (e.g. JavaScript/Python/etc. snippets), effectively detecting the presence of code blocks.

    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
    нем
    -0.08
     compat
    -0.07
     지난
    -0.07
    .Zip
    -0.07
     fever
    -0.06
     physically
    -0.06
     Markup
    -0.06
    han
    -0.06
    MouseEvent
    -0.06
    iphy
    -0.06
    POSITIVE LOGITS
    ("/");↵
    0.07
    ">'
    0.06
    /Dk
    0.06
    ัญช
    0.06
     چگونه
    0.06
    awai
    0.06
    >{$
    0.06
    .NEW
    0.06
    }}">{{$
    0.06
     AVC
    0.06
    Activations Density 0.008%

    No Known Activations