© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68478
    Prev
    Next
    INDEX
    Explanations

    bib

    np_max-act · gemini-2.0-flash

    This neuron identifies markers of a bibliography section (e.g. the “bib­li­o­gra­phy” heading and related tokens).

    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
    agenta
    -0.08
    Qual
    -0.07
    quests
    -0.07
     Guill
    -0.07
     tr
    -0.06
    quest
    -0.06
     nltk
    -0.06
    airport
    -0.06
    CCI
    -0.06
    uffix
    -0.06
    POSITIVE LOGITS
    ційно
    0.06
    =/
    0.06
     transactions
    0.06
     число
    0.06
     Giáo
    0.06
     répond
    0.06
     coverage
    0.06
     Larry
    0.06
     Sans
    0.06
    _ROM
    0.06
    Activations Density 0.001%

    No Known Activations