© 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. 129803
    Prev
    Next
    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: this neuron detects when the text asks about achieving something “in a simple (or easy) way.”

    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
     exciting
    -0.07
     priority
    -0.07
     grit
    -0.06
     interrogation
    -0.06
     pursuit
    -0.06
     Ludwig
    -0.06
     saw
    -0.06
     utrecht
    -0.06
    unchecked
    -0.06
    .eql
    -0.06
    POSITIVE LOGITS
    ولة
    0.07
    Bulletin
    0.06
    ária
    0.06
    bef
    0.06
     표현
    0.06
     p
    0.06
    etler
    0.06
    quine
    0.06
    ประเทศไทย
    0.06
     /(
    0.06
    Activations Density 0.047%

    No Known Activations