Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85650
    Prev
    Next
    INDEX
    Explanations

    HTML/XML code

    np_max-act · gemini-2.0-flash

    This neuron detects the “xygen” sequence in Doxygen‐generated metadata (i.e. parts of the “generator” content tags).

    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
    =list
    -0.07
    保存
    -0.07
    ='';↵
    -0.06
    Videos
    -0.06
    sizlik
    -0.06
     shortcomings
    -0.06
    WW
    -0.06
     detox
    -0.06
    ık
    -0.06
    ekkür
    -0.06
    POSITIVE LOGITS
     đau
    0.07
    (rhs
    0.06
    (gp
    0.06
    hook
    0.06
    KeyEvent
    0.06
    悲
    0.06
    helm
    0.06
    .openqa
    0.06
    钱
    0.06
    _SHARED
    0.06
    Activations Density 0.001%

    No Known Activations