© 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. 90764
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    The neuron fires whenever the text refers to the model’s knowledge or training cutoff date.

    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
     Tempo
    -0.07
     hostel
    -0.06
    [].
    -0.06
    <Card
    -0.06
    ，他
    -0.06
     rough
    -0.06
    't
    -0.06
    Strength
    -0.06
     represents
    -0.06
    ительно
    -0.05
    POSITIVE LOGITS
    _OPTIONS
    0.07
     renov
    0.07
     команд
    0.07
    用品
    0.07
     영어
    0.07
     TECHNO
    0.06
     tiểu
    0.06
    frontend
    0.06
    .APPLICATION
    0.06
    θεν
    0.06
    Activations Density 0.018%

    No Known Activations