Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 130804
    Prev
    Next
    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash

    This neuron detects the occurrence of the word “also” marking parenthetical alternative names (e.g. “also known as …”)

    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
     demokrat
    -0.07
    湾
    -0.06
     launching
    -0.06
    Successful
    -0.06
    اته
    -0.06
    llx
    -0.06
     Rp
    -0.06
    'hui
    -0.06
    بور
    -0.06
    รรค
    -0.06
    POSITIVE LOGITS
     getInput
    0.07
     granting
    0.06
     Nie
    0.06
     contamination
    0.06
     Reception
    0.06
     paving
    0.06
     Каб
    0.06
     cupboard
    0.06
     kendi
    0.06
    아이
    0.06
    Activations Density 0.003%

    No Known Activations