© 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. 92407
    Prev
    Next
    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash

    The neuron fires when text includes exclusivity markers, in particular the word “only.”

    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
     Encoder
    -0.07
    Headers
    -0.07
     incon
    -0.06
     Thread
    -0.06
     },
↵
↵
    -0.06
    creation
    -0.06
    лат
    -0.06
     [...]↵↵
    -0.06
    XmlElement
    -0.06
     congen
    -0.06
    POSITIVE LOGITS
    .Internal
    0.07
     only
    0.07
    裏
    0.06
    \Persistence
    0.06
     Sadece
    0.06
    Only
    0.06
    .tintColor
    0.06
    _STENCIL
    0.06
     arrayWith
    0.06
    DetailsService
    0.06
    Activations Density 0.029%

    No Known Activations