© 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. 54222
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron never fires on any of the tokens shown—i.e. it appears to be inactive (a “dead” neuron) on these inputs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    references to educational institutions and academic achievements.

    oai_token-act-pair · gpt-4o-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
    /categories
    -0.06
    าน
    -0.06
     msgid
    -0.06
    -American
    -0.06
    enqueue
    -0.06
    -black
    -0.06
    -year
    -0.06
     Jazeera
    -0.06
     страны
    -0.06
     bars
    -0.06
    POSITIVE LOGITS
    385
    0.07
    /max
    0.07
    glich
    0.06
     Luis
    0.06
    _ETH
    0.06
     gloves
    0.06
     totaling
    0.06
    OW
    0.06
    لع
    0.06
    OPS
    0.06
    Activations Density 0.013%

    No Known Activations