Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8033
    Prev
    Next
    INDEX
    Explanations

    tiredness

    np_max-act · gemini-2.0-flash

    This neuron detects the phrase “after a long, stressful day.”

    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
    (DB
    -0.07
     Voor
    -0.07
    imei
    -0.06
    .Toast
    -0.06
    ンジ
    -0.06
    壊
    -0.06
    773
    -0.06
    슴
    -0.06
    folder
    -0.06
     Feld
    -0.06
    POSITIVE LOGITS
     *&
    0.07
    location
    0.07
    /Header
    0.07
    ุคคล
    0.06
    KNOWN
    0.06
     chmod
    0.06
     fantastic
    0.06
     loos
    0.06
     significantly
    0.06
     ()
    ↵
    0.06
    Activations Density 0.037%

    No Known Activations