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

    Neuronpedia

    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. 110522
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron does not respond to any tokens (it remains inactive across all inputs).

    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
    Monkey
    -0.07
     Katy
    -0.07
    texture
    -0.06
    668
    -0.06
     Cristina
    -0.06
    .fire
    -0.06
     calm
    -0.06
    .loop
    -0.06
    269
    -0.06
     spokesman
    -0.06
    POSITIVE LOGITS
    ologické
    0.07
     dobr
    0.07
    .OrdinalIgnoreCase
    0.07
    няти
    0.06
    (__('
    0.06
    <bool
    0.06
     Plus
    0.06
    .alpha
    0.06
     drove
    0.06
     khoản
    0.06
    Activations Density 0.046%

    No Known Activations