© 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
    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. 108868
    Prev
    Next
    INDEX
    Explanations

    calories per day

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of caloric information, especially numeric calorie values and references to calorie-restricted diets.

    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
    bm
    -0.06
    _rel
    -0.06
    츠
    -0.06
    _Two
    -0.06
     BAT
    -0.06
     CTL
    -0.06
     بندی
    -0.06
     Reynolds
    -0.06
    ुब
    -0.06
     playback
    -0.06
    POSITIVE LOGITS
    	Http
    0.07
    (intent
    0.07
    economic
    0.07
    yntaxException
    0.07
    advance
    0.06
     jsonObject
    0.06
    (QtGui
    0.06
     Incorpor
    0.06
    lomou
    0.06
     bude
    0.06
    Activations Density 0.003%

    No Known Activations