© 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. 29448
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron flags shell pipelines that use text‐filtering utilities (e.g. grep and awk) to extract or format fields.

    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
    귀
    -0.07
    conditionally
    -0.07
    ！↵
    -0.07
     查询
    -0.07
     Mickey
    -0.07
     Crushing
    -0.07
    nets
    -0.07
     AWS
    -0.07
    -tools
    -0.06
     NORMAL
    -0.06
    POSITIVE LOGITS
     ört
    0.06
    _episode
    0.06
     elders
    0.06
     골
    0.06
    一页
    0.06
    λά
    0.06
     jenter
    0.06
    训
    0.06
     jour
    0.05
     Offer
    0.05
    Activations Density 0.089%

    No Known Activations