© 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. 44262
    Prev
    Next
    INDEX
    Explanations

    location, proximity

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric expressions and nearby location words that express spatial distance or proximity (e.g. “3 miles from,” “near,” “blocks away”).

    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
     endian
    -0.07
    _One
    -0.07
     ทาง
    -0.06
    zá
    -0.06
    date
    -0.06
    疗
    -0.06
    ิการ
    -0.06
     seit
    -0.06
    ительных
    -0.06
    _skin
    -0.06
    POSITIVE LOGITS
    abyrin
    0.06
     plead
    0.06
     tert
    0.06
     skype
    0.06
    .getStatus
    0.06
    ,—
    0.06
     argued
    0.06
    ‌سی
    0.06
     hopefully
    0.06
    %).↵↵
    0.06
    Activations Density 0.021%

    No Known Activations