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. 85855
    Prev
    Next
    INDEX
    Explanations

    m

    np_max-act · gemini-2.0-flash

    The neuron fires on short technical fragments or abbreviations—especially tokens like “Res,” “die,” “D,” and similar brief letter‐sequences that occur in chemical/material names.

    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
    caps
    -0.07
     主
    -0.07
    York
    -0.07
     너
    -0.06
     붙
    -0.06
    IDTH
    -0.06
    -signed
    -0.06
     事
    -0.06
    -blue
    -0.06
    :{↵
    -0.06
    POSITIVE LOGITS
    .ImageField
    0.07
    navbarSupportedContent
    0.06
    ]↵↵↵↵
    0.06
                                  ↵
    0.06
    出版社
    0.06
     γλώ
    0.06
     wasn
    0.06
     ];
    ↵
    0.06
     xứ
    0.06
     ug
    0.06
    Activations Density 0.197%

    No Known Activations