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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84685
    Prev
    Next
    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash

    This neuron activates on the occurrence of the “Summary” label marking the start of the summary section.

    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
     wink
    -0.06
     مخ
    -0.06
     آدم
    -0.06
    ]}>↵
    -0.06
     TVs
    -0.06
     []);↵
    -0.06
    ContentAlignment
    -0.06
    .='
    -0.06
    	Run
    -0.06
    encia
    -0.06
    POSITIVE LOGITS
     cpt
    0.07
     Ž
    0.07
     NL
    0.06
     caste
    0.06
    atas
    0.06
     vyt
    0.06
     Practice
    0.06
     Throwable
    0.06
     withdrawal
    0.06
     toe
    0.06
    Activations Density 0.001%

    No Known Activations