© 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. 109063
    Prev
    Next
    INDEX
    Explanations

    URLs and technical language

    np_max-act · gemini-2.0-flash

    The neuron is essentially inactive (a “dead” neuron) and does not consistently respond to any particular token pattern.

    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
    BitConverter
    -0.07
    Parsing
    -0.07
     گذشته
    -0.06
     thép
    -0.06
    буд
    -0.06
    벤
    -0.06
    ’à
    -0.06
     мех
    -0.06
    епти
    -0.05
    _UNIQUE
    -0.05
    POSITIVE LOGITS
    oss
    0.08
    αν
    0.07
    acus
    0.07
     obviously
    0.07
     지방
    0.07
    uan
    0.07
     Declaration
    0.07
     staged
    0.07
     happens
    0.07
    (ca
    0.07
    Activations Density 0.003%

    No Known Activations