© 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
    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. 56024
    Prev
    Next
    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of doing something “at home” (e.g. home or at-home remedies).

    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
     pantalla
    -0.06
    _DIRECT
    -0.06
    Finished
    -0.06
     plano
    -0.06
    剑
    -0.06
     Крім
    -0.06
    伯
    -0.06
     tarea
    -0.06
    	address
    -0.06
     checkbox
    -0.05
    POSITIVE LOGITS
    ;",↵
    0.07
     smr
    0.07
    بيرة
    0.07
    ớt
    0.07
    templ
    0.06
     используется
    0.06
     Libre
    0.06
     Fir
    0.06
       ↵↵
    0.06
     Dhabi
    0.06
    Activations Density 0.004%

    No Known Activations