© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7872
    Prev
    Next
    INDEX
    Explanations

    Redacted/missing information

    np_max-act · gemini-2.0-flash

    This neuron responds to placeholder tokens representing entity names or IDs (e.g., “NAME_1,” “NAME_2”).

    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
    ipping
    -0.07
     Benny
    -0.06
    opia
    -0.06
    West
    -0.06
     playful
    -0.06
    atabases
    -0.06
    Swipe
    -0.06
     sequences
    -0.06
     Airport
    -0.06
    (training
    -0.06
    POSITIVE LOGITS
    ….
    0.08
    瑟
    0.06
    …
    0.06
    ||
    0.06
    ων
    0.06
    虫
    0.06
     cứng
    0.06
     hut
    0.06
     míst
    0.06
     �
    0.06
    Activations Density 0.045%

    No Known Activations