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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44354
    Prev
    Next
    INDEX
    Explanations

    chemical compositions

    np_max-act · gemini-2.0-flash

    The neuron is triggered by occurrences of “glycer” (as in glycerol, glycerinate, glycerin) in the text.

    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
    itud
    -0.07
     Nigeria
    -0.07
    lld
    -0.07
     Tanzania
    -0.07
    _sp
    -0.06
     TX
    -0.06
     Thur
    -0.06
    Pg
    -0.06
     تازه
    -0.06
    ahu
    -0.06
    POSITIVE LOGITS
     інтер
    0.07
     розрах
    0.07
    /',↵
    0.07
    .containsKey
    0.06
     royalty
    0.06
     sqrt
    0.06
    配
    0.06
     dns
    0.06
     fiscal
    0.06
    вропей
    0.06
    Activations Density 0.002%

    No Known Activations