© 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. 54444
    Prev
    Next
    INDEX
    Explanations

    body protection

    np_max-act · gemini-2.0-flash

    commands related to safety and protective equipment.

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

    This neuron activates on mentions of protective gear covering the hands or feet (e.g., gloves, mittens, gauntlets, boots, sandals).

    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
    iễn
    -0.07
     particularly
    -0.06
    ाइस
    -0.06
     تعیین
    -0.06
     NoSuch
    -0.06
     Zhao
    -0.06
     getCurrent
    -0.06
    认为
    -0.06
     respons
    -0.06
     시행
    -0.06
    POSITIVE LOGITS
    _FMT
    0.06
            ↵        ↵
    0.06
    sss
    0.06
    лагод
    0.06
    Third
    0.06
    .TEST
    0.06
     twentieth
    0.06
    ilt
    0.06
     Support
    0.06
    Fourth
    0.06
    Activations Density 0.014%

    No Known Activations