© 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. 6996
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “decrement” (e.g. in data-ng-click handlers).

    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
    řev
    -0.07
    igen
    -0.06
     فو
    -0.06
    dados
    -0.06
     黄
    -0.06
    -com
    -0.06
    672
    -0.06
    Algorithm
    -0.06
    emption
    -0.06
     EDT
    -0.06
    POSITIVE LOGITS
     учит
    0.07
    NegativeButton
    0.07
     città
    0.06
     Ama
    0.06
     (~
    0.06
    .spaceBetween
    0.06
     rawData
    0.06
    ificador
    0.06
     имеет
    0.06
    Mer
    0.06
    Activations Density 0.099%

    No Known Activations