© 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. 89037
    Prev
    Next
    INDEX
    Explanations

    time related

    np_max-act · gemini-2.0-flash

    The neuron fires on words that refer to timing or immediacy (e.g. “time,” “instant”).

    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
     arou
    -0.08
     nude
    -0.07
     horny
    -0.07
    西
    -0.06
     Observatory
    -0.06
     zoekt
    -0.06
     sürec
    -0.06
    .offsetHeight
    -0.06
     Gesture
    -0.06
    AWS
    -0.06
    POSITIVE LOGITS
     hardship
    0.06
     мик
    0.06
    492
    0.06
    /database
    0.06
    iversity
    0.06
     closets
    0.06
     التح
    0.06
     Randall
    0.06
    /create
    0.06
    Ana
    0.06
    Activations Density 0.029%

    No Known Activations