© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 123265
    Prev
    Next
    INDEX
    Explanations

    CPU

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of computing hardware—especially the token “CPU” (and to a lesser extent “GPU”) when discussing where or how to run models.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    questions related to AI models and their requirements.

    oai_token-act-pair · gpt-4o-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
     ARISING
    -0.08
     emergency
    -0.07
    キング
    -0.07
    дая
    -0.06
    IZE
    -0.06
    �
    -0.06
    uggestions
    -0.06
     subplot
    -0.06
    average
    -0.06
    ITIZE
    -0.06
    POSITIVE LOGITS
    extension
    0.06
    以及
    0.06
     innate
    0.06
    <TextView
    0.06
     appellant
    0.06
    /text
    0.06
     cotton
    0.06
    .Provider
    0.06
     dec
    0.06
    informatics
    0.06
    Activations Density 0.003%

    No Known Activations