© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 110810
    Prev
    Next
    INDEX
    Explanations

    locations of objects

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of colored containers (e.g. “red box,” “yellow box”) that specify object locations.

    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
     T
    -0.06
    UU
    -0.06
    .Build
    -0.06
     =='
    -0.06
    _OPCODE
    -0.06
    AVE
    -0.06
     cud
    -0.06
    trs
    -0.06
    bearing
    -0.06
    TU
    -0.06
    POSITIVE LOGITS
    러운
    0.07
     yelling
    0.07
    บาล
    0.06
     ------------------------------------------------------------
    0.06
     Cassandra
    0.06
    结构
    0.06
    -bel
    0.06
    .requireNonNull
    0.06
     yat
    0.06
    _crypto
    0.06
    Activations Density 0.004%

    No Known Activations