© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30019
    Prev
    Next
    INDEX
    Explanations

    Transient

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the standalone word “Transient,” as used to label section headings or paper titles.

    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
     собі
    -0.07
     kırmızı
    -0.07
     робот
    -0.06
    igate
    -0.06
     ridiculously
    -0.06
     dohod
    -0.06
     способом
    -0.06
     Gold
    -0.06
     gold
    -0.06
    给我
    -0.06
    POSITIVE LOGITS
     transient
    0.10
     Packet
    0.08
    ‰
    0.07
     Trav
    0.07
    ES
    0.07
     เก
    0.07
     oste
    0.07
    /bl
    0.07
    _transient
    0.06
    observer
    0.06
    Activations Density 0.002%

    No Known Activations