© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6738
    Prev
    Next
    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash

    The neuron detects XML namespace attributes (e.g. the “xml:lang” declaration).

    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
    нит
    -0.07
     spouses
    -0.06
     weave
    -0.06
    aksi
    -0.06
     Reyn
    -0.06
    Markup
    -0.06
     suggestive
    -0.06
    urvey
    -0.06
     Pepsi
    -0.06
     MT
    -0.06
    POSITIVE LOGITS
    Ba
    0.07
     древ
    0.07
    �
    0.07
    .Expressions
    0.07
     систем
    0.06
    ぞ
    0.06
    :
    0.06
    平均
    0.06
    래
    0.06
    权限
    0.06
    Activations Density 0.000%

    No Known Activations