© 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. 110541
    Prev
    Next
    INDEX
    Explanations

    Yellow

    np_max-act · gemini-2.0-flash

    The neuron activates on the word “yellow,” i.e. it detects occurrences of that color term.

    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
    ़ो
    -0.08
     Ops
    -0.08
     core
    -0.07
     orc
    -0.07
     спри
    -0.07
    ASF
    -0.07
     Forex
    -0.07
    _done
    -0.07
    (rec
    -0.07
     Rome
    -0.07
    POSITIVE LOGITS
     yellow
    0.13
     Yellow
    0.12
    Yellow
    0.11
    YELLOW
    0.09
    yellow
    0.08
     Yellowstone
    0.08
     amber
    0.08
     여
    0.07
    -yellow
    0.07
    Blue
    0.07
    Activations Density 0.006%

    No Known Activations