© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44199
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron detects temporal framing phrases, especially “in recent years,” at the start of discourse.

    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
     parks
    -0.06
    107
    -0.06
     кир
    -0.06
    .SC
    -0.06
     TTC
    -0.06
    .Est
    -0.06
    428
    -0.06
    	wx
    -0.06
     Ph
    -0.06
    Hom
    -0.06
    POSITIVE LOGITS
     <<"
    0.07
    gence
    0.07
    ality
    0.06
    .Filter
    0.06
     ascertain
    0.06
    ґ
    0.06
    ，而且
    0.06
    اجع
    0.06
    ็
    0.06
     ************************************************************************
    0.06
    Activations Density 0.028%

    No Known Activations