© 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. 73741
    Prev
    Next
    INDEX
    Explanations

    room

    np_max-act · gemini-2.0-flash

    The neuron activates on words naming or referring to indoor spatial locations (e.g. “room,” “corner”).

    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
    lang
    -0.07
    oren
    -0.07
    \F
    -0.06
    ucchini
    -0.06
    Excel
    -0.06
    Happy
    -0.06
    hq
    -0.06
     oggi
    -0.06
    Lost
    -0.06
    charging
    -0.06
    POSITIVE LOGITS
     тро
    0.06
     neut
    0.06
     QLD
    0.06
     mM
    0.06
     Reception
    0.06
     room
    0.06
     karş
    0.06
    .comboBox
    0.06
     gereken
    0.06
     نور
    0.06
    Activations Density 0.019%

    No Known Activations