© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 56977
    Prev
    Next
    INDEX
    Explanations

    consultation comment

    np_max-act · gemini-2.0-flash

    references to community development and local infrastructure improvements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on references to public consultation or comment periods—mentions of consultations, comment windows, and related timing.

    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
    пор
    -0.07
    卓
    -0.07
     strdup
    -0.07
     density
    -0.06
     해
    -0.06
     renovation
    -0.06
     willingness
    -0.06
     MANAGEMENT
    -0.06
    �
    -0.06
    sizlik
    -0.06
    POSITIVE LOGITS
     Prev
    0.08
    ляет
    0.07
    (G
    0.07
    NN
    0.07
     sabah
    0.07
    >O
    0.06
     interacts
    0.06
    rought
    0.06
    \:
    0.06
    aggio
    0.06
    Activations Density 0.012%

    No Known Activations