© 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. 44378
    Prev
    Next
    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash

    This neuron detects numerical geographic distance measurements or coordinate values (e.g., “south 2.857…,” “north 2.783…”) indicating location.

    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
    잖
    -0.07
    arding
    -0.07
    _tensors
    -0.06
    rende
    -0.06
    급
    -0.06
    _COUNTER
    -0.06
    要
    -0.06
    曾
    -0.06
    ilere
    -0.06
    يرا
    -0.06
    POSITIVE LOGITS
     sö
    0.06
     tm
    0.06
    stitial
    0.06
     SST
    0.06
     Мор
    0.06
    _ST
    0.06
    =head
    0.06
     üçüncü
    0.06
     firmware
    0.06
     recursively
    0.06
    Activations Density 0.006%

    No Known Activations