© 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. 89695
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash

    The neuron flags declarative error or exception messages that state a feature isn’t supported (e.g. “This … does not support …”).

    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
    lin
    -0.06
    оряд
    -0.06
    exercise
    -0.06
    yeah
    -0.06
    Procedure
    -0.06
    iles
    -0.06
     principles
    -0.06
     disable
    -0.06
    t
    -0.06
    zych
    -0.06
    POSITIVE LOGITS
    reur
    0.07
     Cyr
    0.07
     uplifting
    0.07
     μέ
    0.06
     Grey
    0.06
     nedir
    0.06
    COMMAND
    0.06
    ῆ
    0.06
    юн
    0.06
    359
    0.06
    Activations Density 0.011%

    No Known Activations