© 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. 54027
    Prev
    Next
    INDEX
    Explanations

    programming input/parameters

    np_max-act · gemini-2.0-flash

    The neuron fires on usage examples telling you to “pass in” a string to a function—e.g. phrases like “if you pass in the string…”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    functions related to string manipulation and character handling.

    oai_token-act-pair · gpt-4o-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
    (IT
    -0.07
     Evolution
    -0.07
    CheckedChangeListener
    -0.07
     otel
    -0.07
    _alarm
    -0.06
     ALOG
    -0.06
    iationException
    -0.06
    DFS
    -0.06
    XMLElement
    -0.06
     ambit
    -0.06
    POSITIVE LOGITS
    مول
    0.06
    onda
    0.06
    "},↵
    0.06
     Tomas
    0.06
    ποι
    0.06
    pha
    0.06
    лося
    0.06
    kiem
    0.06
    .${
    0.06
    edian
    0.06
    Activations Density 0.031%

    No Known Activations