© 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. 91716
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron detects French first-person offers of help (e.g. “Je suis là pour vous aider …”).

    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
    -lo
    -0.07
     smallest
    -0.06
    �
    -0.06
     presses
    -0.06
     serpent
    -0.06
    YSTEM
    -0.06
     Publishers
    -0.06
    Internet
    -0.06
     Merry
    -0.06
     metadata
    -0.06
    POSITIVE LOGITS
    мах
    0.07
    €�
    0.07
    .hasMore
    0.06
    	Collection
    0.06
     GetLastError
    0.06
     起
    0.06
    rades
    0.06
     ''),↵
    0.06
    цю
    0.06
    キング
    0.06
    Activations Density 0.059%

    No Known Activations