© 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. 128807
    Prev
    Next
    INDEX
    Explanations

    white black

    np_max-act · gemini-2.0-flash

    The neuron activates on color descriptors (e.g. white, black, yellow).

    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
     سكان
    -0.07
    (columns
    -0.07
     diver
    -0.06
     quadratic
    -0.06
    会议
    -0.06
    uppies
    -0.06
     pojist
    -0.06
     контроль
    -0.06
    ۱۳۹
    -0.06
     Alle
    -0.06
    POSITIVE LOGITS
     bastante
    0.07
     labelText
    0.07
     завер
    0.06
     UObject
    0.06
     кіль
    0.06
     isActive
    0.06
     einfach
    0.06
    .red
    0.06
     Monument
    0.06
     mName
    0.06
    Activations Density 0.012%

    No Known Activations