© 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. 6968
    Prev
    Next
    INDEX
    Explanations

    Is/are

    np_max-act · gemini-2.0-flash

    technical vocabulary related to software and engineering roles.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron never activates on any input, i.e. it doesn’t detect any meaningful pattern.

    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
    _head
    -0.07
     hedge
    -0.06
    __)
    -0.06
    (src
    -0.06
     divert
    -0.06
     suggestive
    -0.06
     detach
    -0.06
    DBG
    -0.06
    Cómo
    -0.06
     Palmer
    -0.06
    POSITIVE LOGITS
    _AUT
    0.07
    اصيل
    0.06
     ARE
    0.06
    _articles
    0.06
    :*
    0.06
    .art
    0.06
     çalışmalar
    0.06
     AVL
    0.06
    ня
    0.06
     را
    0.06
    Activations Density 0.033%

    No Known Activations