© 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. 13073
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron activates on bibliography‐style citations and reference markers (e.g. items like “Westinghouse [3]” and similar citation 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
    格式
    -0.06
    掛
    -0.06
     رز
    -0.06
    ในร
    -0.06
    _dt
    -0.06
     وسط
    -0.06
     PG
    -0.06
    Neighbor
    -0.06
    OMP
    -0.06
    UFFIX
    -0.06
    POSITIVE LOGITS
    _flash
    0.07
    .Requires
    0.07
    [top
    0.07
     viewWillAppear
    0.06
    stateParams
    0.06
     ridicule
    0.06
     unwanted
    0.06
     ClassNotFoundException
    0.06
    ames
    0.06
     Wort
    0.06
    Activations Density 0.053%

    No Known Activations