© 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. 129807
    Prev
    Next
    INDEX
    Explanations

    up/build

    np_max-act · gemini-2.0-flash

    The neuron is primarily triggered by the term “build-up” (and its subparts like “build” + “up”), i.e. mentions of accumulation.

    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
     яс
    -0.07
    щее
    -0.07
     Shan
    -0.06
     rescue
    -0.06
     relativ
    -0.06
    esto
    -0.06
     också
    -0.06
    annel
    -0.06
     Integral
    -0.06
    ắ
    -0.06
    POSITIVE LOGITS
    ---------↵↵
    0.07
     Wright
    0.06
    package
    0.06
     بال
    0.06
     Bai
    0.06
     PreparedStatement
    0.06
     objectType
    0.06
     exagger
    0.06
    _HISTORY
    0.06
     buildup
    0.06
    Activations Density 0.007%

    No Known Activations